{"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/answer-generation","name":"Answer Generation","slug":"answer-generation","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":280,"papers_with_code":111,"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":1},"benchmarks":[{"leaderboard":"/sota/answer-generation-on-weibopolls","slug":"answer-generation-on-weibopolls","dataset":"WeiboPolls","dataset_url":"/dataset/weibopolls","rows_in_archive":3,"metrics":["ROUGE-1","ROUGE-L","BLEU-1","BLEU-3"],"first_row_in_archive_order":{"model":"UniPoll","paper_title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","paper_url":"/paper/unipoll-a-unified-social-media-poll","paper_date":"2023-06-12","arxiv_id":"2306.06851","code_links":[{"title":"X1AOX1A/UniPoll","url":"https://github.com/X1AOX1A/UniPoll"}],"syntology":null}},{"leaderboard":"/sota/answer-generation-on-cicero","slug":"answer-generation-on-cicero","dataset":"CICERO","dataset_url":"/dataset/cicero","rows_in_archive":2,"metrics":["ROUGE"],"first_row_in_archive_order":{"model":"T5-large pre-trained on GLUCOSE","paper_title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","paper_url":"/paper/cicero-a-dataset-for-contextualized","paper_date":"2022-03-25","arxiv_id":"2203.13926","code_links":[{"title":"declare-lab/CICERO","url":"https://github.com/declare-lab/CICERO"}],"syntology":null}}],"datasets":[{"url":"/dataset/qampari","name":"QAMPARI","full_name":"","num_papers_in_archive":19},{"url":"/dataset/cicero","name":"CICERO","full_name":"Contextualized Commonsense Inference in Dialogues","num_papers_in_archive":12},{"url":"/dataset/weibopolls","name":"WeiboPolls","full_name":"","num_papers_in_archive":3},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/natural-language-inference","name":"Natural Language Inference"}],"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":280,"of_with_code":111,"tagged_in_all":280,"counts":{"archive_papers_tagged":280,"with_a_code_link":111,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":280,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","repositories_listed":57,"syntology":{"n":31,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}},"official":null}},{"url":"/paper/regnlp-in-action-facilitating-compliance","slug":"regnlp-in-action-facilitating-compliance","title":"RIRAG: Regulatory Information Retrieval and Answer Generation","date":"2024-09-09","arxiv_id":"2409.05677","repositories_listed":4,"syntology":null},{"url":"/paper/zusammenqa-data-augmentation-with-specialized","slug":"zusammenqa-data-augmentation-with-specialized","title":"ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System","date":"2022-05-30","arxiv_id":"2205.14981","repositories_listed":3,"syntology":null},{"url":"/paper/vogue-answer-verbalization-through-multi-task","slug":"vogue-answer-verbalization-through-multi-task","title":"VOGUE: Answer Verbalization through Multi-Task Learning","date":"2021-06-24","arxiv_id":"2106.13316","repositories_listed":3,"syntology":null},{"url":"/paper/lrta-a-transparent-neural-symbolic-reasoning","slug":"lrta-a-transparent-neural-symbolic-reasoning","title":"LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering","date":"2020-11-21","arxiv_id":"2011.10731","repositories_listed":3,"syntology":null},{"url":"/paper/dataset-and-neural-recurrent-sequence","slug":"dataset-and-neural-recurrent-sequence","title":"Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering","date":"2016-07-21","arxiv_id":"1607.06275","repositories_listed":3,"syntology":null},{"url":"/paper/mm-instruct-generated-visual-instructions-for","slug":"mm-instruct-generated-visual-instructions-for","title":"MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment","date":"2024-06-28","arxiv_id":"2406.19736","repositories_listed":2,"syntology":null},{"url":"/paper/poisonedrag-knowledge-poisoning-attacks-to","slug":"poisonedrag-knowledge-poisoning-attacks-to","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-02-12","arxiv_id":"2402.07867","repositories_listed":2,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":5,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/poisonedrag-knowledge-poisoning-attacks-to#ran","syntology_url":"https://syntology.ai/paper/2402.07867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07867"}},"official":{"repos":["sleeepeer/poisonedrag"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/surgical-vqla-transformer-with-gated-vision","slug":"surgical-vqla-transformer-with-gated-vision","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-05-19","arxiv_id":"2305.11692","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/surgical-vqla-transformer-with-gated-vision#ran","syntology_url":"https://syntology.ai/paper/2305.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11692"}},"official":{"repos":["longbai1006/surgical-vqla"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/qampari-an-open-domain-question-answering","slug":"qampari-an-open-domain-question-answering","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","date":"2022-05-25","arxiv_id":"2205.12665","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qampari-an-open-domain-question-answering#ran","syntology_url":"https://syntology.ai/paper/2205.12665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12665"}},"official":null}},{"url":"/paper/mumuqa-multimedia-multi-hop-news-question","slug":"mumuqa-multimedia-multi-hop-news-question","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","date":"2021-12-20","arxiv_id":"2112.10728","repositories_listed":2,"syntology":null},{"url":"/paper/it-is-ai-s-turn-to-ask-human-a-question","slug":"it-is-ai-s-turn-to-ask-human-a-question","title":"It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books","date":"2021-09-08","arxiv_id":"2109.03423","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-multi-document-reader","slug":"end-to-end-training-of-multi-document-reader","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","date":"2021-06-09","arxiv_id":"2106.05346","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}},"official":{"repos":["DevSinghSachan/emdr2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/quiz-style-question-generation-for-news","slug":"quiz-style-question-generation-for-news","title":"Quiz-Style Question Generation for News Stories","date":"2021-02-18","arxiv_id":"2102.09094","repositories_listed":2,"syntology":null},{"url":"/paper/asking-questions-the-human-way-scalable","slug":"asking-questions-the-human-way-scalable","title":"Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus","date":"2020-01-27","arxiv_id":"2002.00748","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/asking-questions-the-human-way-scalable#ran","syntology_url":"https://syntology.ai/paper/2002.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00748"}},"official":{"repos":["bangliu/ACS-QG"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/rmit-adm-s-at-the-sigir-2025-liverag","slug":"rmit-adm-s-at-the-sigir-2025-liverag","title":"RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge","date":"2025-06-17","arxiv_id":"2506.14516","repositories_listed":1,"syntology":null},{"url":"/paper/tablerag-a-retrieval-augmented-generation","slug":"tablerag-a-retrieval-augmented-generation","title":"TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning","date":"2025-06-12","arxiv_id":"2506.10380","repositories_listed":1,"syntology":null},{"url":"/paper/ecorag-evidentiality-guided-compression-for","slug":"ecorag-evidentiality-guided-compression-for","title":"ECoRAG: Evidentiality-guided Compression for Long Context RAG","date":"2025-06-05","arxiv_id":"2506.05167","repositories_listed":1,"syntology":null},{"url":"/paper/o-2-searcher-a-searching-based-agent-model","slug":"o-2-searcher-a-searching-based-agent-model","title":"O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering","date":"2025-05-22","arxiv_id":"2505.16582","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 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","sample_list":"/paper/o-2-searcher-a-searching-based-agent-model#ran","syntology_url":"https://syntology.ai/paper/2505.16582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16582"}},"official":{"repos":["acade-mate/o2-searcher"],"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"]}}},{"url":"/paper/gui-g1-understanding-r1-zero-like-training","slug":"gui-g1-understanding-r1-zero-like-training","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","date":"2025-05-21","arxiv_id":"2505.15810","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/gui-g1-understanding-r1-zero-like-training#ran","syntology_url":"https://syntology.ai/paper/2505.15810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15810"}},"official":{"repos":["yuqi-zhou/gui-g1"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-atlas-of-in-context-learning-how","slug":"the-atlas-of-in-context-learning-how","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","date":"2025-05-21","arxiv_id":"2505.15807","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/the-atlas-of-in-context-learning-how#ran","syntology_url":"https://syntology.ai/paper/2505.15807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15807"}},"official":{"repos":["pkhdipraja/in-context-atlas"],"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/process-vs-outcome-reward-which-is-better-for","slug":"process-vs-outcome-reward-which-is-better-for","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14069","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/process-vs-outcome-reward-which-is-better-for#ran","syntology_url":"https://syntology.ai/paper/2505.14069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14069"}},"official":{"repos":["wlzhang2020/reasonrag"],"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":["official"]}}},{"url":"/paper/kg-qagen-a-knowledge-graph-based-framework","slug":"kg-qagen-a-knowledge-graph-based-framework","title":"KG-QAGen: A Knowledge-Graph-Based Framework for Systematic Question Generation and Long-Context LLM Evaluation","date":"2025-05-18","arxiv_id":"2505.12495","repositories_listed":1,"syntology":null},{"url":"/paper/rag-vr-leveraging-retrieval-augmented","slug":"rag-vr-leveraging-retrieval-augmented","title":"RAG-VR: Leveraging Retrieval-Augmented Generation for 3D Question Answering in VR Environments","date":"2025-04-11","arxiv_id":"2504.08256","repositories_listed":1,"syntology":null},{"url":"/paper/localized-definitions-and-distributed","slug":"localized-definitions-and-distributed","title":"Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching","date":"2025-04-03","arxiv_id":"2504.02976","repositories_listed":1,"syntology":null},{"url":"/paper/metaladder-ascending-mathematical-solution","slug":"metaladder-ascending-mathematical-solution","title":"MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer","date":"2025-03-19","arxiv_id":"2503.14891","repositories_listed":1,"syntology":null},{"url":"/paper/conversational-gold-evaluating-personalized","slug":"conversational-gold-evaluating-personalized","title":"Conversational Gold: Evaluating Personalized Conversational Search System using Gold Nuggets","date":"2025-03-12","arxiv_id":"2503.09902","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-complex-question-answering-on-long","slug":"zero-shot-complex-question-answering-on-long","title":"Zero-Shot Complex Question-Answering on Long Scientific Documents","date":"2025-03-04","arxiv_id":"2503.02695","repositories_listed":1,"syntology":null},{"url":"/paper/egonormia-benchmarking-physical-social-norm","slug":"egonormia-benchmarking-physical-social-norm","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","date":"2025-02-27","arxiv_id":"2502.20490","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egonormia-benchmarking-physical-social-norm#ran","syntology_url":"https://syntology.ai/paper/2502.20490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20490"}},"official":{"repos":["open-social-world/egonormia"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-hybrid-approach-to-information-retrieval","slug":"a-hybrid-approach-to-information-retrieval","title":"A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts","date":"2025-02-24","arxiv_id":"2502.16767","repositories_listed":1,"syntology":null},{"url":"/paper/peerqa-a-scientific-question-answering","slug":"peerqa-a-scientific-question-answering","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","date":"2025-02-19","arxiv_id":"2502.13668","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 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) · 2 unverified","sample_list":"/paper/peerqa-a-scientific-question-answering#ran","syntology_url":"https://syntology.ai/paper/2502.13668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13668"}},"official":{"repos":["ukplab/peerqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/trustrag-an-information-assistant-with","slug":"trustrag-an-information-assistant-with","title":"TrustRAG: An Information Assistant with Retrieval Augmented Generation","date":"2025-02-19","arxiv_id":"2502.13719","repositories_listed":1,"syntology":null},{"url":"/paper/let-the-ai-conspiracy-begin-language-model","slug":"let-the-ai-conspiracy-begin-language-model","title":"HSI: Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models","date":"2025-02-09","arxiv_id":"2502.05945","repositories_listed":1,"syntology":null},{"url":"/paper/prot2chat-protein-llm-with-early-fusion-of","slug":"prot2chat-protein-llm-with-early-fusion-of","title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","date":"2025-02-07","arxiv_id":"2502.06846","repositories_listed":1,"syntology":null},{"url":"/paper/mramg-bench-a-beyondtext-benchmark-for","slug":"mramg-bench-a-beyondtext-benchmark-for","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","date":"2025-02-06","arxiv_id":"2502.04176","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-state-space-models-for","slug":"multilingual-state-space-models-for","title":"Multilingual State Space Models for Structured Question Answering in Indic Languages","date":"2025-02-01","arxiv_id":"2502.01673","repositories_listed":1,"syntology":null},{"url":"/paper/improving-retrieval-augmented-generation","slug":"improving-retrieval-augmented-generation","title":"Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning","date":"2025-01-25","arxiv_id":"2501.15228","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2501.15228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15228"}},"official":{"repos":["chenyiqun/mmoa-rag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-human-data-aligning-multimodal-large","slug":"beyond-human-data-aligning-multimodal-large","title":"Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution","date":"2024-12-20","arxiv_id":"2412.15650","repositories_listed":1,"syntology":null},{"url":"/paper/bioragent-a-retrieval-augmented-generation","slug":"bioragent-a-retrieval-augmented-generation","title":"BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific Q&A","date":"2024-12-16","arxiv_id":"2412.12358","repositories_listed":1,"syntology":null},{"url":"/paper/ragviz-diagnose-and-visualize-retrieval","slug":"ragviz-diagnose-and-visualize-retrieval","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","date":"2024-11-04","arxiv_id":"2411.01751","repositories_listed":1,"syntology":null},{"url":"/paper/an-adaptive-framework-for-generating","slug":"an-adaptive-framework-for-generating","title":"An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms","date":"2024-10-23","arxiv_id":"2410.17694","repositories_listed":1,"syntology":null},{"url":"/paper/do-rag-systems-cover-what-matters-evaluating","slug":"do-rag-systems-cover-what-matters-evaluating","title":"Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage","date":"2024-10-20","arxiv_id":"2410.15531","repositories_listed":1,"syntology":null},{"url":"/paper/medlogic-aqa-enhancing-medical-question","slug":"medlogic-aqa-enhancing-medical-question","title":"MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures","date":"2024-10-20","arxiv_id":"2410.15463","repositories_listed":1,"syntology":null},{"url":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","repositories_listed":1,"syntology":null},{"url":"/paper/easyrag-efficient-retrieval-augmented","slug":"easyrag-efficient-retrieval-augmented","title":"EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations","date":"2024-10-14","arxiv_id":"2410.10315","repositories_listed":1,"syntology":null},{"url":"/paper/multi-granularity-contrastive-cross-modal","slug":"multi-granularity-contrastive-cross-modal","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","date":"2024-10-12","arxiv_id":"2410.09379","repositories_listed":1,"syntology":null},{"url":"/paper/auditwen-an-open-source-large-language-model","slug":"auditwen-an-open-source-large-language-model","title":"AuditWen:An Open-Source Large Language Model for Audit","date":"2024-10-09","arxiv_id":"2410.10873","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-markets-a-multilingual-benchmark-to","slug":"unlocking-markets-a-multilingual-benchmark-to","title":"Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering","date":"2024-09-24","arxiv_id":"2409.16025","repositories_listed":1,"syntology":null},{"url":"/paper/halo-hallucination-analysis-and-learning","slug":"halo-hallucination-analysis-and-learning","title":"HALO: Hallucination Analysis and Learning Optimization to Empower LLMs with Retrieval-Augmented Context for Guided Clinical Decision Making","date":"2024-09-16","arxiv_id":"2409.10011","repositories_listed":1,"syntology":null},{"url":"/paper/debate-on-graph-a-flexible-and-reliable","slug":"debate-on-graph-a-flexible-and-reliable","title":"Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models","date":"2024-09-05","arxiv_id":"2409.03155","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debate-on-graph-a-flexible-and-reliable#ran","syntology_url":"https://syntology.ai/paper/2409.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03155"}},"official":{"repos":["reml-group/dog"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/genetic-approach-to-mitigate-hallucination-in","slug":"genetic-approach-to-mitigate-hallucination-in","title":"Genetic Approach to Mitigate Hallucination in Generative IR","date":"2024-08-25","arxiv_id":"2409.00085","repositories_listed":1,"syntology":null},{"url":"/paper/fastfid-improve-inference-efficiency-of-open","slug":"fastfid-improve-inference-efficiency-of-open","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","date":"2024-08-12","arxiv_id":"2408.06333","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/fastfid-improve-inference-efficiency-of-open#ran","syntology_url":"https://syntology.ai/paper/2408.06333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06333"}},"official":{"repos":["thunlp/fastfid"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/unleashing-artificial-cognition-integrating","slug":"unleashing-artificial-cognition-integrating","title":"Unleashing Artificial Cognition: Integrating Multiple AI Systems","date":"2024-08-09","arxiv_id":"2408.04910","repositories_listed":1,"syntology":null},{"url":"/paper/an-interactive-multi-modal-query-answering","slug":"an-interactive-multi-modal-query-answering","title":"An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models","date":"2024-07-05","arxiv_id":"2407.04217","repositories_listed":1,"syntology":null},{"url":"/paper/trustuqa-a-trustful-framework-for-unified","slug":"trustuqa-a-trustful-framework-for-unified","title":"TrustUQA: A Trustful Framework for Unified Structured Data Question Answering","date":"2024-06-27","arxiv_id":"2406.18916","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":0,"n_honours":4,"n_violates":1,"n_no_contract":2,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trustuqa-a-trustful-framework-for-unified#ran","syntology_url":"https://syntology.ai/paper/2406.18916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18916"}},"official":{"repos":["zjukg/trustuqa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieve-plan-generation-an-iterative","slug":"retrieve-plan-generation-an-iterative","title":"Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation","date":"2024-06-21","arxiv_id":"2406.14979","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":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieve-plan-generation-an-iterative#ran","syntology_url":"https://syntology.ai/paper/2406.14979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14979"}},"official":{"repos":["haruhi-sudo/RPG"],"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/climretrieve-a-benchmarking-dataset-for","slug":"climretrieve-a-benchmarking-dataset-for","title":"ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures","date":"2024-06-14","arxiv_id":"2406.09818","repositories_listed":1,"syntology":null},{"url":"/paper/fairytaleqa-translated-enabling-educational","slug":"fairytaleqa-translated-enabling-educational","title":"FairytaleQA Translated: Enabling Educational Question and Answer Generation in Less-Resourced Languages","date":"2024-06-06","arxiv_id":"2406.04233","repositories_listed":1,"syntology":null},{"url":"/paper/an-information-bottleneck-perspective-for","slug":"an-information-bottleneck-perspective-for","title":"An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation","date":"2024-06-03","arxiv_id":"2406.01549","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-information-bottleneck-perspective-for#ran","syntology_url":"https://syntology.ai/paper/2406.01549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01549"}},"official":{"repos":["zhukun1020/noisefilter_ib"],"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/do-vision-language-decoders-use-images-and","slug":"do-vision-language-decoders-use-images-and","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","date":"2024-04-29","arxiv_id":"2404.18624","repositories_listed":1,"syntology":null},{"url":"/paper/medifact-at-mediqa-m3g-2024-medical-question","slug":"medifact-at-mediqa-m3g-2024-medical-question","title":"MediFact at MEDIQA-M3G 2024: Medical Question Answering in Dermatology with Multimodal Learning","date":"2024-04-27","arxiv_id":"2405.01583","repositories_listed":1,"syntology":null},{"url":"/paper/on-few-shot-prompting-for-controllable","slug":"on-few-shot-prompting-for-controllable","title":"On Few-Shot Prompting for Controllable Question-Answer Generation in Narrative Comprehension","date":"2024-04-03","arxiv_id":"2404.02800","repositories_listed":1,"syntology":null},{"url":"/paper/can-llms-correct-physicians-yet-investigating","slug":"can-llms-correct-physicians-yet-investigating","title":"Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain","date":"2024-03-29","arxiv_id":"2403.20288","repositories_listed":1,"syntology":null},{"url":"/paper/are-large-language-models-good-at-utility","slug":"are-large-language-models-good-at-utility","title":"Are Large Language Models Good at Utility Judgments?","date":"2024-03-28","arxiv_id":"2403.19216","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"3 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/are-large-language-models-good-at-utility#ran","syntology_url":"https://syntology.ai/paper/2403.19216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19216"}},"official":{"repos":["ict-bigdatalab/utility_judgments"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/harnessing-multi-role-capabilities-of-large","slug":"harnessing-multi-role-capabilities-of-large","title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","date":"2024-03-08","arxiv_id":"2403.05217","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-think-step-by-step-a-mechanistic","slug":"how-to-think-step-by-step-a-mechanistic","title":"How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning","date":"2024-02-28","arxiv_id":"2402.18312","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 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) · 1 unverified","sample_list":"/paper/how-to-think-step-by-step-a-mechanistic#ran","syntology_url":"https://syntology.ai/paper/2402.18312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18312"}},"official":{"repos":["joykirat18/how-to-think-step-by-step"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-training-cross-lingual-open-domain","slug":"pre-training-cross-lingual-open-domain","title":"Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision","date":"2024-02-26","arxiv_id":"2402.16508","repositories_listed":1,"syntology":null},{"url":"/paper/towards-generative-abstract-reasoning","slug":"towards-generative-abstract-reasoning","title":"Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection","date":"2024-01-18","arxiv_id":"2401.09966","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-generative-abstract-reasoning#ran","syntology_url":"https://syntology.ai/paper/2401.09966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09966"}},"official":{"repos":["fudanvi/generative-abstract-reasoning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-the-impact-of-false-negatives-in","slug":"mitigating-the-impact-of-false-negatives-in","title":"Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization","date":"2023-12-30","arxiv_id":"2401.00165","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"1 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mitigating-the-impact-of-false-negatives-in#ran","syntology_url":"https://syntology.ai/paper/2401.00165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00165"}},"official":{"repos":["wangskygit/passage-sieve"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm4eda-emerging-progress-in-large-language","slug":"llm4eda-emerging-progress-in-large-language","title":"LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation","date":"2023-12-28","arxiv_id":"2401.12224","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/dcqa-document-level-chart-question-answering","slug":"dcqa-document-level-chart-question-answering","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","date":"2023-10-29","arxiv_id":"2310.18983","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-and-multimodal","slug":"large-language-models-and-multimodal","title":"Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation","date":"2023-10-21","arxiv_id":"2310.14025","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-and-multimodal#ran","syntology_url":"https://syntology.ai/paper/2310.14025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14025"}},"official":{"repos":["anastasiakrith/multimodal-retrieval-for-vwsd"],"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/improving-question-generation-with-multi","slug":"improving-question-generation-with-multi","title":"Improving Question Generation with Multi-level Content Planning","date":"2023-10-20","arxiv_id":"2310.13512","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-retrieval-augmented-reader-models","slug":"optimizing-retrieval-augmented-reader-models","title":"Optimizing Retrieval-augmented Reader Models via Token Elimination","date":"2023-10-20","arxiv_id":"2310.13682","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/optimizing-retrieval-augmented-reader-models#ran","syntology_url":"https://syntology.ai/paper/2310.13682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13682"}},"official":{"repos":["mosheber/token_elimination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/graphextqa-a-benchmark-for-evaluating-graph","slug":"graphextqa-a-benchmark-for-evaluating-graph","title":"GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models","date":"2023-10-12","arxiv_id":"2310.08487","repositories_listed":1,"syntology":null},{"url":"/paper/abstracting-concept-changing-rules-for","slug":"abstracting-concept-changing-rules-for","title":"Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems","date":"2023-07-15","arxiv_id":"2307.07734","repositories_listed":1,"syntology":null},{"url":"/paper/answer-mining-from-a-pool-of-images-towards","slug":"answer-mining-from-a-pool-of-images-towards","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","date":"2023-06-29","arxiv_id":"2306.16713","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"7 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/answer-mining-from-a-pool-of-images-towards#ran","syntology_url":"https://syntology.ai/paper/2306.16713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16713"}},"official":{"repos":["Abhiram4572/mi_bart"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-chatgpt-a-biomedical-expert-exploring-the","slug":"is-chatgpt-a-biomedical-expert-exploring-the","title":"Is ChatGPT a Biomedical Expert? -- Exploring the Zero-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2023-06-28","arxiv_id":"2306.16108","repositories_listed":1,"syntology":null},{"url":"/paper/unipoll-a-unified-social-media-poll","slug":"unipoll-a-unified-social-media-poll","title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","date":"2023-06-12","arxiv_id":"2306.06851","repositories_listed":1,"syntology":null},{"url":"/paper/reta-llm-a-retrieval-augmented-large-language","slug":"reta-llm-a-retrieval-augmented-large-language","title":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit","date":"2023-06-08","arxiv_id":"2306.05212","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reta-llm-a-retrieval-augmented-large-language#ran","syntology_url":"https://syntology.ai/paper/2306.05212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05212"}},"official":{"repos":["ruc-gsai/yulan-ir"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-practical-toolkit-for-multilingual-question","slug":"a-practical-toolkit-for-multilingual-question","title":"A Practical Toolkit for Multilingual Question and Answer Generation","date":"2023-05-27","arxiv_id":"2305.17416","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-comparison-of-lm-based-question","slug":"an-empirical-comparison-of-lm-based-question","title":"An Empirical Comparison of LM-based Question and Answer Generation Methods","date":"2023-05-26","arxiv_id":"2305.17002","repositories_listed":1,"syntology":null},{"url":"/paper/xpqa-cross-lingual-product-question-answering","slug":"xpqa-cross-lingual-product-question-answering","title":"xPQA: Cross-Lingual Product Question Answering across 12 Languages","date":"2023-05-16","arxiv_id":"2305.09249","repositories_listed":1,"syntology":null},{"url":"/paper/vtqa-visual-text-question-answering-via","slug":"vtqa-visual-text-question-answering-via","title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning","date":"2023-03-05","arxiv_id":"2303.02635","repositories_listed":1,"syntology":null},{"url":"/paper/can-chatgpt-assess-human-personalities-a","slug":"can-chatgpt-assess-human-personalities-a","title":"Can ChatGPT Assess Human Personalities? A General Evaluation Framework","date":"2023-03-01","arxiv_id":"2303.01248","repositories_listed":1,"syntology":null},{"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/improving-low-resource-question-answering","slug":"improving-low-resource-question-answering","title":"Combining Data Generation and Active Learning for Low-Resource Question Answering","date":"2022-11-27","arxiv_id":"2211.14880","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-model-with-unlikelihood","slug":"unified-multimodal-model-with-unlikelihood","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","date":"2022-11-23","arxiv_id":"2211.13235","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-augmented-visual-question-answering","slug":"retrieval-augmented-visual-question-answering","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","date":"2022-10-07","arxiv_id":"2210.03809","repositories_listed":1,"syntology":null},{"url":"/paper/tag-boosting-text-vqa-via-text-aware-visual","slug":"tag-boosting-text-vqa-via-text-aware-visual","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","date":"2022-08-03","arxiv_id":"2208.01813","repositories_listed":1,"syntology":null},{"url":"/paper/elqa-a-corpus-of-questions-and-answers-about","slug":"elqa-a-corpus-of-questions-and-answers-about","title":"ELQA: A Corpus of Metalinguistic Questions and Answers about English","date":"2022-05-01","arxiv_id":"2205.00395","repositories_listed":1,"syntology":null},{"url":"/paper/cicero-a-dataset-for-contextualized","slug":"cicero-a-dataset-for-contextualized","title":"CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues","date":"2022-03-25","arxiv_id":"2203.13926","repositories_listed":1,"syntology":null},{"url":"/paper/scai-qrecc-shared-task-on-conversational","slug":"scai-qrecc-shared-task-on-conversational","title":"SCAI-QReCC Shared Task on Conversational Question Answering","date":"2022-01-26","arxiv_id":"2201.11094","repositories_listed":1,"syntology":null},{"url":"/paper/towards-personalized-answer-generation-in-e","slug":"towards-personalized-answer-generation-in-e","title":"Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling","date":"2021-12-27","arxiv_id":"2112.13556","repositories_listed":1,"syntology":null},{"url":"/paper/kat-a-knowledge-augmented-transformer-for","slug":"kat-a-knowledge-augmented-transformer-for","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","date":"2021-12-16","arxiv_id":"2112.08614","repositories_listed":1,"syntology":null},{"url":"/paper/change-detection-meets-visual-question","slug":"change-detection-meets-visual-question","title":"Change Detection Meets Visual Question Answering","date":"2021-12-12","arxiv_id":"2112.06343","repositories_listed":1,"syntology":null},{"url":"/paper/engage-the-public-poll-question-generation","slug":"engage-the-public-poll-question-generation","title":"Engage the Public: Poll Question Generation for Social Media Posts","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/one-question-answering-model-for-many","slug":"one-question-answering-model-for-many","title":"One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval","date":"2021-07-26","arxiv_id":"2107.11976","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":0,"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/one-question-answering-model-for-many#ran","syntology_url":"https://syntology.ai/paper/2107.11976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11976"}},"official":{"repos":["AkariAsai/CORA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knowing-more-about-questions-can-help","slug":"knowing-more-about-questions-can-help","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","date":"2021-06-02","arxiv_id":"2106.01494","repositories_listed":1,"syntology":null}],"syntology_records":28,"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":28,"papers_where_code_ran_first_page":"/task/answer-generation/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/answer-generation/papers/2","json":"/task/answer-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/answer-generation/papers/3","json":"/task/answer-generation/papers/3.json","rows":80},{"order":"ran","page":1,"of":1,"url":"/task/answer-generation/papers/ran/1","json":"/task/answer-generation/papers/ran/1.json","rows":28}],"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":"fa11226320258aedf1fc0f0f0e801f6e36dec6ba44ff334480a479bf694407a3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}