{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multi-hop-question-answering","name":"Multi-hop Question Answering","slug":"multi-hop-question-answering","description_markdown":null,"categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":202,"papers_with_code":92,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/multi-hop-question-answering-on-concurrentqa","slug":"multi-hop-question-answering-on-concurrentqa","dataset":"ConcurrentQA","dataset_url":"/dataset/simran-arora","rows_in_archive":1,"metrics":["Answer F1"],"first_row_in_archive_order":{"model":"Multi-hop Dense Passage Retriever (MDR)","paper_title":"Reasoning over Public and Private Data in Retrieval-Based Systems","paper_url":"/paper/reasoning-over-public-and-private-data-in","paper_date":"2022-03-14","arxiv_id":"2203.11027","code_links":[{"title":"facebookresearch/concurrentqa","url":"https://github.com/facebookresearch/concurrentqa"}],"syntology":null}},{"leaderboard":"/sota/multi-hop-question-answering-on-musique-ans","slug":"multi-hop-question-answering-on-musique-ans","dataset":"MuSiQue-Ans","dataset_url":"/dataset/musique-ans","rows_in_archive":1,"metrics":["An","Sp"],"first_row_in_archive_order":{"model":"Beam Retrieval","paper_title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","paper_url":"/paper/beam-retrieval-general-end-to-end-retrieval","paper_date":"2023-08-17","arxiv_id":"2308.08973","code_links":[{"title":"ShayekhBinIslam/openrag","url":"https://github.com/ShayekhBinIslam/openrag"},{"title":"canghongjian/beam_retriever","url":"https://github.com/canghongjian/beam_retriever"},{"title":"Alab-NII/2wikimultihop","url":"https://github.com/Alab-NII/2wikimultihop"}],"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/beam-retrieval-general-end-to-end-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.08973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08973"}},"official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/musique-ans","name":"MuSiQue-Ans","full_name":"","num_papers_in_archive":10},{"url":"/dataset/spartqa-1","name":"SPARTQA -","full_name":"SPAtial Reasoning on Textual Question Answering.","num_papers_in_archive":9},{"url":"/dataset/simran-arora","name":"ConcurrentQA Benchmark","full_name":"","num_papers_in_archive":3},{"url":"/dataset/multiq","name":"MultiQ","full_name":"MultiQ","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":202,"of_with_code":92,"tagged_in_all":202,"counts":{"archive_papers_tagged":202,"with_a_code_link":92,"where_syntology_ran_a_sample":32,"not_listed_spam_title":0,"listed":202,"listed_where_code_ran":32,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","repositories_listed":6,"syntology":{"n":25,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":17,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/qa-gnn-reasoning-with-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2104.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06378"}},"official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/190409380","slug":"190409380","title":"Repurposing Entailment for Multi-Hop Question Answering Tasks","date":"2019-04-20","arxiv_id":"1904.09380","repositories_listed":4,"syntology":null},{"url":"/paper/beam-retrieval-general-end-to-end-retrieval","slug":"beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","arxiv_id":"2308.08973","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/beam-retrieval-general-end-to-end-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.08973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08973"}},"official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/musique-multi-hop-questions-via-single-hop","slug":"musique-multi-hop-questions-via-single-hop","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","date":"2021-08-02","arxiv_id":"2108.00573","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/musique-multi-hop-questions-via-single-hop#ran","syntology_url":"https://syntology.ai/paper/2108.00573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00573"}},"official":{"repos":["stonybrooknlp/musique"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-hop-question-answering-via-reasoning","slug":"multi-hop-question-answering-via-reasoning","title":"Multi-hop Question Answering via Reasoning Chains","date":"2019-10-07","arxiv_id":"1910.02610","repositories_listed":3,"syntology":null},{"url":"/paper/hipporag-neurobiologically-inspired-long-term","slug":"hipporag-neurobiologically-inspired-long-term","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","date":"2024-05-23","arxiv_id":"2405.14831","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hipporag-neurobiologically-inspired-long-term#ran","syntology_url":"https://syntology.ai/paper/2405.14831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14831"}},"official":{"repos":["osu-nlp-group/hipporag"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deepedit-knowledge-editing-as-decoding-with","slug":"deepedit-knowledge-editing-as-decoding-with","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","date":"2024-01-19","arxiv_id":"2401.10471","repositories_listed":2,"syntology":null},{"url":"/paper/mquake-assessing-knowledge-editing-in","slug":"mquake-assessing-knowledge-editing-in","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","date":"2023-05-24","arxiv_id":"2305.14795","repositories_listed":2,"syntology":null},{"url":"/paper/can-language-models-solve-graph-problems-in","slug":"can-language-models-solve-graph-problems-in","title":"Can Language Models Solve Graph Problems in Natural Language?","date":"2023-05-17","arxiv_id":"2305.10037","repositories_listed":2,"syntology":{"n":22,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/can-language-models-solve-graph-problems-in#ran","syntology_url":"https://syntology.ai/paper/2305.10037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10037"}},"official":{"repos":["arthur-heng/nlgraph"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-the-effectiveness-of-the-underlying","slug":"analyzing-the-effectiveness-of-the-underlying","title":"Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering","date":"2023-02-12","arxiv_id":"2302.05963","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-label-smoothing-on-multi-hop","slug":"rethinking-label-smoothing-on-multi-hop","title":"Rethinking Label Smoothing on Multi-hop Question Answering","date":"2022-12-19","arxiv_id":"2212.09512","repositories_listed":2,"syntology":null},{"url":"/paper/improving-multi-hop-question-answering-over","slug":"improving-multi-hop-question-answering-over","title":"Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/hybridqa-a-dataset-of-multi-hop-question","slug":"hybridqa-a-dataset-of-multi-hop-question","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","date":"2020-04-15","arxiv_id":"2004.07347","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hybridqa-a-dataset-of-multi-hop-question#ran","syntology_url":"https://syntology.ai/paper/2004.07347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07347"}},"official":{"repos":["wenhuchen/HybridQA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/cognitive-graph-for-multi-hop-reading","slug":"cognitive-graph-for-multi-hop-reading","title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","date":"2019-05-14","arxiv_id":"1905.05460","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cognitive-graph-for-multi-hop-reading#ran","syntology_url":"https://syntology.ai/paper/1905.05460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05460"}},"official":{"repos":["THUDM/CogQA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hotpotqa-a-dataset-for-diverse-explainable","slug":"hotpotqa-a-dataset-for-diverse-explainable","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","date":"2018-09-25","arxiv_id":"1809.09600","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hotpotqa-a-dataset-for-diverse-explainable#ran","syntology_url":"https://syntology.ai/paper/1809.09600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.09600"}},"official":{"repos":["hotpotqa/hotpot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/commonsense-for-generative-multi-hop-question","slug":"commonsense-for-generative-multi-hop-question","title":"Commonsense for Generative Multi-Hop Question Answering Tasks","date":"2018-09-17","arxiv_id":"1809.06309","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/commonsense-for-generative-multi-hop-question#ran","syntology_url":"https://syntology.ai/paper/1809.06309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06309"}},"official":{"repos":["yicheng-w/CommonSenseMultiHopQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dynamic-chunking-and-selection-for-reading","slug":"dynamic-chunking-and-selection-for-reading","title":"Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models","date":"2025-06-01","arxiv_id":"2506.00773","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-chunking-and-selection-for-reading#ran","syntology_url":"https://syntology.ai/paper/2506.00773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00773"}},"official":{"repos":["ecnu-text-computing/dcs"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-external-knowledge-input-beyond","slug":"scaling-external-knowledge-input-beyond","title":"Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration","date":"2025-05-27","arxiv_id":"2505.21471","repositories_listed":1,"syntology":null},{"url":"/paper/knowtrace-bootstrapping-iterative-retrieval","slug":"knowtrace-bootstrapping-iterative-retrieval","title":"KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing","date":"2025-05-26","arxiv_id":"2505.20245","repositories_listed":1,"syntology":null},{"url":"/paper/masksearch-a-universal-pre-training-framework","slug":"masksearch-a-universal-pre-training-framework","title":"MASKSEARCH: A Universal Pre-Training Framework to Enhance Agentic Search Capability","date":"2025-05-26","arxiv_id":"2505.20285","repositories_listed":1,"syntology":null},{"url":"/paper/self-critique-guided-iterative-reasoning-for","slug":"self-critique-guided-iterative-reasoning-for","title":"Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering","date":"2025-05-25","arxiv_id":"2505.19112","repositories_listed":1,"syntology":null},{"url":"/paper/situatedthinker-grounding-llm-reasoning-with","slug":"situatedthinker-grounding-llm-reasoning-with","title":"SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking","date":"2025-05-25","arxiv_id":"2505.19300","repositories_listed":1,"syntology":null},{"url":"/paper/hopweaver-synthesizing-authentic-multi-hop","slug":"hopweaver-synthesizing-authentic-multi-hop","title":"HopWeaver: Synthesizing Authentic Multi-Hop Questions Across Text Corpora","date":"2025-05-21","arxiv_id":"2505.15087","repositories_listed":1,"syntology":null},{"url":"/paper/masking-in-multi-hop-qa-an-analysis-of-how","slug":"masking-in-multi-hop-qa-an-analysis-of-how","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","date":"2025-05-16","arxiv_id":"2505.11754","repositories_listed":1,"syntology":null},{"url":"/paper/focus-merge-rank-improved-question-answering","slug":"focus-merge-rank-improved-question-answering","title":"Focus, Merge, Rank: Improved Question Answering Based on Semi-structured Knowledge Bases","date":"2025-05-14","arxiv_id":"2505.09246","repositories_listed":1,"syntology":null},{"url":"/paper/treehop-generate-and-filter-next-query","slug":"treehop-generate-and-filter-next-query","title":"TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering","date":"2025-04-28","arxiv_id":"2504.20114","repositories_listed":1,"syntology":null},{"url":"/paper/collab-rag-boosting-retrieval-augmented","slug":"collab-rag-boosting-retrieval-augmented","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","date":"2025-04-07","arxiv_id":"2504.04915","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/collab-rag-boosting-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2504.04915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04915"}},"official":{"repos":["ritaranx/collab-rag"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/retrieval-augmented-generation-with-1","slug":"retrieval-augmented-generation-with-1","title":"Retrieval-Augmented Generation with Hierarchical Knowledge","date":"2025-03-13","arxiv_id":"2503.10150","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/retrieval-augmented-generation-with-1#ran","syntology_url":"https://syntology.ai/paper/2503.10150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10150"}},"official":{"repos":["hhy-huang/HiRAG"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/levelrag-enhancing-retrieval-augmented","slug":"levelrag-enhancing-retrieval-augmented","title":"LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers","date":"2025-02-25","arxiv_id":"2502.18139","repositories_listed":1,"syntology":null},{"url":"/paper/mintqa-a-multi-hop-question-answering","slug":"mintqa-a-multi-hop-question-answering","title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","date":"2024-12-22","arxiv_id":"2412.17032","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-editing-with-dynamic-knowledge","slug":"knowledge-editing-with-dynamic-knowledge","title":"Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering","date":"2024-12-18","arxiv_id":"2412.13782","repositories_listed":1,"syntology":null},{"url":"/paper/lost-in-the-middle-and-in-between-enhancing","slug":"lost-in-the-middle-and-in-between-enhancing","title":"Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA","date":"2024-12-13","arxiv_id":"2412.10079","repositories_listed":1,"syntology":null},{"url":"/paper/kg-retriever-efficient-knowledge-indexing-for","slug":"kg-retriever-efficient-knowledge-indexing-for","title":"KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models","date":"2024-12-07","arxiv_id":"2412.05547","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/kg-retriever-efficient-knowledge-indexing-for#ran","syntology_url":"https://syntology.ai/paper/2412.05547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05547"}},"official":{"repos":["bai-lab/kg-retriever"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-chunking-learning-efficient-text#ran","syntology_url":"https://syntology.ai/paper/2410.12788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12788"}},"official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-ai-reasoning-a-hamiltonian","slug":"optimizing-ai-reasoning-a-hamiltonian","title":"Optimizing AI Reasoning: A Hamiltonian Dynamics Approach to Multi-Hop Question Answering","date":"2024-10-06","arxiv_id":"2410.04415","repositories_listed":1,"syntology":null},{"url":"/paper/2409-14057","slug":"2409-14057","title":"Co-occurrence is not Factual Association in Language Models","date":"2024-09-21","arxiv_id":"2409.14057","repositories_listed":1,"syntology":null},{"url":"/paper/iteration-of-thought-leveraging-inner","slug":"iteration-of-thought-leveraging-inner","title":"Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning","date":"2024-09-19","arxiv_id":"2409.12618","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-multi-hop-videoqa-in-long-form","slug":"grounded-multi-hop-videoqa-in-long-form","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","date":"2024-08-26","arxiv_id":"2408.14469","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-multi-hop-videoqa-in-long-form#ran","syntology_url":"https://syntology.ai/paper/2408.14469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14469"}},"official":null}},{"url":"/paper/rcone-rough-cone-embedding-for-multi-hop","slug":"rcone-rough-cone-embedding-for-multi-hop","title":"RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs","date":"2024-08-21","arxiv_id":"2408.11526","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-retrieval-augmented-generation","slug":"hierarchical-retrieval-augmented-generation","title":"Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering","date":"2024-08-20","arxiv_id":"2408.11875","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hierarchical-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2408.11875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11875"}},"official":{"repos":["2282588541a/hirag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/efficientrag-efficient-retriever-for-multi","slug":"efficientrag-efficient-retriever-for-multi","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","date":"2024-08-08","arxiv_id":"2408.04259","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficientrag-efficient-retriever-for-multi#ran","syntology_url":"https://syntology.ai/paper/2408.04259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04259"}},"official":{"repos":["nil-zhuang/efficientrag-official"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/compact-compressing-retrieved-documents","slug":"compact-compressing-retrieved-documents","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","date":"2024-07-12","arxiv_id":"2407.09014","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":3,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 3 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/compact-compressing-retrieved-documents#ran","syntology_url":"https://syntology.ai/paper/2407.09014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09014"}},"official":{"repos":["dmis-lab/compact"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/arigraph-learning-knowledge-graph-world","slug":"arigraph-learning-knowledge-graph-world","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","date":"2024-07-05","arxiv_id":"2407.04363","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/arigraph-learning-knowledge-graph-world#ran","syntology_url":"https://syntology.ai/paper/2407.04363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04363"}},"official":{"repos":["airi-institute/arigraph"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/husky-a-unified-open-source-language-agent","slug":"husky-a-unified-open-source-language-agent","title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning","date":"2024-06-10","arxiv_id":"2406.06469","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/husky-a-unified-open-source-language-agent#ran","syntology_url":"https://syntology.ai/paper/2406.06469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06469"}},"official":{"repos":["agent-husky/husky-v1"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/reflection-reinforced-self-training-for","slug":"reflection-reinforced-self-training-for","title":"Re-ReST: Reflection-Reinforced Self-Training for Language Agents","date":"2024-06-03","arxiv_id":"2406.01495","repositories_listed":1,"syntology":null},{"url":"/paper/single-and-multi-hop-question-answering","slug":"single-and-multi-hop-question-answering","title":"Single and Multi-Hop Question-Answering Datasets for Reticular Chemistry with GPT-4-Turbo","date":"2024-05-03","arxiv_id":"2405.02128","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-enhanced-knowledge-editing-for","slug":"retrieval-enhanced-knowledge-editing-for","title":"Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering","date":"2024-03-28","arxiv_id":"2403.19631","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/retrieval-enhanced-knowledge-editing-for#ran","syntology_url":"https://syntology.ai/paper/2403.19631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19631"}},"official":{"repos":["sycny/rae"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dr3-ask-large-language-models-not-to-give-off","slug":"dr3-ask-large-language-models-not-to-give-off","title":"Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering","date":"2024-03-19","arxiv_id":"2403.12393","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dr3-ask-large-language-models-not-to-give-off#ran","syntology_url":"https://syntology.ai/paper/2403.12393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12393"}},"official":{"repos":["gy915/dr3"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-failure-integrating-negative","slug":"learning-from-failure-integrating-negative","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","date":"2024-02-18","arxiv_id":"2402.11651","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-from-failure-integrating-negative#ran","syntology_url":"https://syntology.ai/paper/2402.11651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11651"}},"official":{"repos":["reason-wang/nat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/longagent-scaling-language-models-to-128k","slug":"longagent-scaling-language-models-to-128k","title":"LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration","date":"2024-02-18","arxiv_id":"2402.11550","repositories_listed":1,"syntology":null},{"url":"/paper/direct-evaluation-of-chain-of-thought-in","slug":"direct-evaluation-of-chain-of-thought-in","title":"Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs","date":"2024-02-17","arxiv_id":"2402.11199","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/direct-evaluation-of-chain-of-thought-in#ran","syntology_url":"https://syntology.ai/paper/2402.11199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11199"}},"official":{"repos":["minhvuong2000/llmreasoncert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-principle-learning-from-mistakes","slug":"in-context-principle-learning-from-mistakes","title":"In-Context Principle Learning from Mistakes","date":"2024-02-08","arxiv_id":"2402.05403","repositories_listed":1,"syntology":null},{"url":"/paper/pokemqa-programmable-knowledge-editing-for","slug":"pokemqa-programmable-knowledge-editing-for","title":"PokeMQA: Programmable knowledge editing for Multi-hop Question Answering","date":"2023-12-23","arxiv_id":"2312.15194","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pokemqa-programmable-knowledge-editing-for#ran","syntology_url":"https://syntology.ai/paper/2312.15194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15194"}},"official":{"repos":["hengrui-gu/pokemqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gnn2r-weakly-supervised-rationale-providing","slug":"gnn2r-weakly-supervised-rationale-providing","title":"GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs","date":"2023-12-04","arxiv_id":"2312.02317","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-guided-global-memory-improves","slug":"uncertainty-guided-global-memory-improves","title":"Uncertainty Guided Global Memory Improves Multi-Hop Question Answering","date":"2023-11-29","arxiv_id":"2311.18151","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-structured-information-for","slug":"leveraging-structured-information-for","title":"Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning","date":"2023-11-07","arxiv_id":"2311.03734","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":13,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/leveraging-structured-information-for#ran","syntology_url":"https://syntology.ai/paper/2311.03734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03734"}},"official":{"repos":["bcdnlp/structure-qa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/self-prompted-chain-of-thought-on-large","slug":"self-prompted-chain-of-thought-on-large","title":"Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning","date":"2023-10-20","arxiv_id":"2310.13552","repositories_listed":1,"syntology":null},{"url":"/paper/screws-a-modular-framework-for-reasoning-with","slug":"screws-a-modular-framework-for-reasoning-with","title":"SCREWS: A Modular Framework for Reasoning with Revisions","date":"2023-09-20","arxiv_id":"2309.13075","repositories_listed":1,"syntology":null},{"url":"/paper/kitlm-domain-specific-knowledge-integration","slug":"kitlm-domain-specific-knowledge-integration","title":"KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering","date":"2023-08-07","arxiv_id":"2308.03638","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-retrieval-augmented-large-language","slug":"enhancing-retrieval-augmented-large-language","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","date":"2023-05-24","arxiv_id":"2305.15294","repositories_listed":1,"syntology":null},{"url":"/paper/search-in-the-chain-towards-the-accurate","slug":"search-in-the-chain-towards-the-accurate","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","date":"2023-04-28","arxiv_id":"2304.14732","repositories_listed":1,"syntology":null},{"url":"/paper/answering-questions-by-meta-reasoning-over","slug":"answering-questions-by-meta-reasoning-over","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","date":"2023-04-25","arxiv_id":"2304.13007","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/answering-questions-by-meta-reasoning-over#ran","syntology_url":"https://syntology.ai/paper/2304.13007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13007"}},"official":{"repos":["oriyor/reasoning-on-cots"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/nature-language-reasoning-a-survey","slug":"nature-language-reasoning-a-survey","title":"Natural Language Reasoning, A Survey","date":"2023-03-26","arxiv_id":"2303.14725","repositories_listed":1,"syntology":null},{"url":"/paper/faithful-chain-of-thought-reasoning","slug":"faithful-chain-of-thought-reasoning","title":"Faithful Chain-of-Thought Reasoning","date":"2023-01-31","arxiv_id":"2301.13379","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/faithful-chain-of-thought-reasoning#ran","syntology_url":"https://syntology.ai/paper/2301.13379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13379"}},"official":{"repos":["veronica320/faithful-cot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-multi-modal-and-multi-hop-question","slug":"enhancing-multi-modal-and-multi-hop-question","title":"Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation","date":"2022-12-16","arxiv_id":"2212.08632","repositories_listed":1,"syntology":null},{"url":"/paper/unikgqa-unified-retrieval-and-reasoning-for","slug":"unikgqa-unified-retrieval-and-reasoning-for","title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","date":"2022-12-02","arxiv_id":"2212.00959","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/unikgqa-unified-retrieval-and-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2212.00959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00959"}},"official":{"repos":["rucaibox/unikgqa"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/locate-then-ask-interpretable-stepwise","slug":"locate-then-ask-interpretable-stepwise","title":"Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering","date":"2022-08-22","arxiv_id":"2208.10297","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-graph-reasoning-fusing-knowledge-and","slug":"explicit-graph-reasoning-fusing-knowledge-and","title":"Explicit Graph Reasoning Fusing Knowledge and Contextual Information for Multi-hop Question Answering","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vimqa-a-vietnamese-dataset-for-advanced","slug":"vimqa-a-vietnamese-dataset-for-advanced","title":"VIMQA: A Vietnamese Dataset for Advanced Reasoning and Explainable Multi-hop Question Answering","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-over-public-and-private-data-in","slug":"reasoning-over-public-and-private-data-in","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","date":"2022-03-14","arxiv_id":"2203.11027","repositories_listed":1,"syntology":null},{"url":"/paper/qa4qg-using-question-answering-to-constrain","slug":"qa4qg-using-question-answering-to-constrain","title":"QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation","date":"2022-02-14","arxiv_id":"2202.06538","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-humans-when-to-defer-to-a-classifier","slug":"teaching-humans-when-to-defer-to-a-classifier","title":"Teaching Humans When To Defer to a Classifier via Exemplars","date":"2021-11-22","arxiv_id":"2111.11297","repositories_listed":1,"syntology":null},{"url":"/paper/improving-embedded-knowledge-graph-multi-hop","slug":"improving-embedded-knowledge-graph-multi-hop","title":"Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning","date":"2021-10-25","arxiv_id":"2110.12679","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-autoregressive-solver-for-scalable","slug":"hybrid-autoregressive-solver-for-scalable","title":"Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration","date":"2021-07-25","arxiv_id":"2107.11879","repositories_listed":1,"syntology":null},{"url":"/paper/analysing-dense-passage-retrieval-for-multi","slug":"analysing-dense-passage-retrieval-for-multi","title":"Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering","date":"2021-06-15","arxiv_id":"2106.08433","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-semantic-graph-construction-and","slug":"dynamic-semantic-graph-construction-and","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","date":"2021-05-25","arxiv_id":"2105.11776","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/dynamic-semantic-graph-construction-and#ran","syntology_url":"https://syntology.ai/paper/2105.11776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11776"}},"official":{"repos":["wwxu21/AMR-SG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transfernet-an-effective-and-transparent","slug":"transfernet-an-effective-and-transparent","title":"TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph","date":"2021-04-15","arxiv_id":"2104.07302","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/transfernet-an-effective-and-transparent#ran","syntology_url":"https://syntology.ai/paper/2104.07302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07302"}},"official":{"repos":["shijx12/TransferNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/multi-step-reasoning-over-unstructured-text","slug":"multi-step-reasoning-over-unstructured-text","title":"Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval","date":"2021-04-13","arxiv_id":"2104.05883","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-step-reasoning-over-unstructured-text#ran","syntology_url":"https://syntology.ai/paper/2104.05883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05883"}},"official":{"repos":["henryzhao5852/BeamDR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/re-improving-multi-hop-question-answering","slug":"re-improving-multi-hop-question-answering","title":"[Re] Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings","date":"2021-01-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/visbert-hidden-state-visualizations-for","slug":"visbert-hidden-state-visualizations-for","title":"VisBERT: Hidden-State Visualizations for Transformers","date":"2020-11-09","arxiv_id":"2011.04507","repositories_listed":1,"syntology":null},{"url":"/paper/constructing-a-multi-hop-qa-dataset-for","slug":"constructing-a-multi-hop-qa-dataset-for","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","date":"2020-11-02","arxiv_id":"2011.01060","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/constructing-a-multi-hop-qa-dataset-for#ran","syntology_url":"https://syntology.ai/paper/2011.01060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01060"}},"official":{"repos":["Alab-NII/2wikimultihop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/less-is-more-data-efficient-complex-question","slug":"less-is-more-data-efficient-complex-question","title":"Less is More: Data-Efficient Complex Question Answering over Knowledge Bases","date":"2020-10-29","arxiv_id":"2010.15881","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-multi-hop-question-answering-by","slug":"unsupervised-multi-hop-question-answering-by","title":"Unsupervised Multi-hop Question Answering by Question Generation","date":"2020-10-23","arxiv_id":"2010.12623","repositories_listed":1,"syntology":null},{"url":"/paper/srlgrn-semantic-role-labeling-graph-reasoning","slug":"srlgrn-semantic-role-labeling-graph-reasoning","title":"SRLGRN: Semantic Role Labeling Graph Reasoning Network","date":"2020-10-07","arxiv_id":"2010.03604","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-alignment-based-iterative","slug":"unsupervised-alignment-based-iterative","title":"Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering","date":"2020-05-04","arxiv_id":"2005.01218","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-and-reducing-non-multifact","slug":"measuring-and-reducing-non-multifact","title":"Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning","date":"2020-05-02","arxiv_id":"2005.00789","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/measuring-and-reducing-non-multifact#ran","syntology_url":"https://syntology.ai/paper/2005.00789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00789"}},"official":{"repos":["stonybrooknlp/dire"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/transformer-xh-multi-evidence-reasoning-with","slug":"transformer-xh-multi-evidence-reasoning-with","title":"Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-graph-network-for-multi-hop","slug":"hierarchical-graph-network-for-multi-hop","title":"Hierarchical Graph Network for Multi-hop Question Answering","date":"2019-11-09","arxiv_id":"1911.03631","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hierarchical-graph-network-for-multi-hop#ran","syntology_url":"https://syntology.ai/paper/1911.03631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03631"}},"official":{"repos":["yuwfan/HGN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-annotate-modularizing-data","slug":"learning-to-annotate-modularizing-data","title":"Learning from Explanations with Neural Execution Tree","date":"2019-11-04","arxiv_id":"1911.01352","repositories_listed":1,"syntology":null},{"url":"/paper/qasc-a-dataset-for-question-answering-via","slug":"qasc-a-dataset-for-question-answering-via","title":"QASC: A Dataset for Question Answering via Sentence Composition","date":"2019-10-25","arxiv_id":"1910.11473","repositories_listed":1,"syntology":null},{"url":"/paper/whats-missing-a-knowledge-gap-guided-approach","slug":"whats-missing-a-knowledge-gap-guided-approach","title":"What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering","date":"2019-09-19","arxiv_id":"1909.09253","repositories_listed":1,"syntology":null},{"url":"/paper/avoiding-reasoning-shortcuts-adversarial","slug":"avoiding-reasoning-shortcuts-adversarial","title":"Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA","date":"2019-06-17","arxiv_id":"1906.07132","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/avoiding-reasoning-shortcuts-adversarial#ran","syntology_url":"https://syntology.ai/paper/1906.07132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.07132"}},"official":{"repos":["jiangycTarheel/Adversarial-MultiHopQA"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":null,"slug":"memento-note-taking-for-your-future-self","title":"Memento: Note-Taking for Your Future Self","date":"2025-06-25","arxiv_id":"2506.20642","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-scaled-graphrag-improving-multi-hop","title":"Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs","date":"2025-06-24","arxiv_id":"2506.19967","repositories_listed":0,"syntology":null},{"url":null,"slug":"kunlunbaizerag-reinforcement-learning-driven","title":"KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models","date":"2025-06-24","arxiv_id":"2506.19466","repositories_listed":0,"syntology":null},{"url":null,"slug":"mental-health-equity-in-llms-leveraging-multi","title":"Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives","date":"2025-06-22","arxiv_id":"2506.18116","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-retrieval-augmented-generation","title":"A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy","date":"2025-06-01","arxiv_id":"2506.04252","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolvesearch-an-iterative-self-evolving","title":"EvolveSearch: An Iterative Self-Evolving Search Agent","date":"2025-05-28","arxiv_id":"2505.22501","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-llm-reasoning-with-dynamic-notes","title":"Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA","date":"2025-05-22","arxiv_id":"2505.16293","repositories_listed":0,"syntology":null},{"url":null,"slug":"belle-a-bi-level-multi-agent-reasoning","title":"BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering","date":"2025-05-17","arxiv_id":"2505.11811","repositories_listed":0,"syntology":null}],"syntology_records":36,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":32,"papers_where_code_ran_first_page":"/task/multi-hop-question-answering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/multi-hop-question-answering/papers/2","json":"/task/multi-hop-question-answering/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/multi-hop-question-answering/papers/3","json":"/task/multi-hop-question-answering/papers/3.json","rows":2},{"order":"ran","page":1,"of":1,"url":"/task/multi-hop-question-answering/papers/ran/1","json":"/task/multi-hop-question-answering/papers/ran/1.json","rows":32}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6aa86d1d3511a5120259af538768ea88552175e32496464aaa4cf858f0f56b8a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}