{"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/hallucination-evaluation","name":"Hallucination Evaluation","slug":"hallucination-evaluation","description_markdown":"Evaluate the ability of LLM to generate non-hallucination text or assess the capability of LLM to recognize hallucinations.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":49,"papers_with_code":29,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/hallueditbench","name":"HalluEditBench","full_name":"","num_papers_in_archive":2},{"url":"/dataset/phd","name":"PhD","full_name":"PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset","num_papers_in_archive":1},{"url":"/dataset/xinhuahallucinations","name":"UHGEvalDataset","full_name":"","num_papers_in_archive":1}],"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":1,"rows_per_page":100,"shown":49,"of":49,"of_with_code":29,"tagged_in_all":49,"counts":{"archive_papers_tagged":49,"with_a_code_link":29,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":49,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":12,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":12,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/hallusionbench-you-see-what-you-think-or-you","slug":"hallusionbench-you-see-what-you-think-or-you","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","date":"2023-10-23","arxiv_id":"2310.14566","repositories_listed":9,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hallusionbench-you-see-what-you-think-or-you#ran","syntology_url":"https://syntology.ai/paper/2310.14566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14566"}},"official":{"repos":["tianyi-lab/hallusionbench"],"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":["listed","official"]}}},{"url":"/paper/autohallusion-automatic-generation-of","slug":"autohallusion-automatic-generation-of","title":"AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models","date":"2024-06-16","arxiv_id":"2406.10900","repositories_listed":3,"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/autohallusion-automatic-generation-of#ran","syntology_url":"https://syntology.ai/paper/2406.10900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10900"}},"official":{"repos":["wuxiyang1996/AutoHallusion"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/helma-a-large-scale-hallucination-evaluation","slug":"helma-a-large-scale-hallucination-evaluation","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","date":"2023-05-19","arxiv_id":"2305.11747","repositories_listed":3,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/helma-a-large-scale-hallucination-evaluation#ran","syntology_url":"https://syntology.ai/paper/2305.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11747"}},"official":{"repos":["RUCAIBox/HaluEval","rucaibox/helma"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/alleviating-hallucinations-of-large-language","slug":"alleviating-hallucinations-of-large-language","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","date":"2023-12-25","arxiv_id":"2312.15710","repositories_listed":2,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 6 unverified","sample_list":"/paper/alleviating-hallucinations-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.15710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15710"}},"official":{"repos":["hiyouga/llama-factory","hillzhang1999/icd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/knowrl-exploring-knowledgeable-reinforcement","slug":"knowrl-exploring-knowledgeable-reinforcement","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","date":"2025-06-24","arxiv_id":"2506.19807","repositories_listed":1,"syntology":null},{"url":"/paper/multihal-multilingual-dataset-for-knowledge","slug":"multihal-multilingual-dataset-for-knowledge","title":"MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations","date":"2025-05-20","arxiv_id":"2505.14101","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-llm-faithfulness-in-rag-with","slug":"benchmarking-llm-faithfulness-in-rag-with","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","date":"2025-05-07","arxiv_id":"2505.04847","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/benchmarking-llm-faithfulness-in-rag-with#ran","syntology_url":"https://syntology.ai/paper/2505.04847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04847"}},"official":{"repos":["vectara/FaithJudge"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-hallucination-of-large-multimodal","slug":"exploring-hallucination-of-large-multimodal","title":"Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation","date":"2025-03-25","arxiv_id":"2503.19622","repositories_listed":1,"syntology":null},{"url":"/paper/2503-01670","slug":"2503-01670","title":"Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization","date":"2025-03-03","arxiv_id":"2503.01670","repositories_listed":1,"syntology":null},{"url":"/paper/treecut-a-synthetic-unanswerable-math-word","slug":"treecut-a-synthetic-unanswerable-math-word","title":"TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation","date":"2025-02-19","arxiv_id":"2502.13442","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/treecut-a-synthetic-unanswerable-math-word#ran","syntology_url":"https://syntology.ai/paper/2502.13442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13442"}},"official":{"repos":["j-bagel/treecut-math"],"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/dahl-domain-specific-automated-hallucination","slug":"dahl-domain-specific-automated-hallucination","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","date":"2024-11-14","arxiv_id":"2411.09255","repositories_listed":1,"syntology":null},{"url":"/paper/ddfav-remote-sensing-large-vision-language","slug":"ddfav-remote-sensing-large-vision-language","title":"DDFAV: Remote Sensing Large Vision Language Models Dataset and Evaluation Benchmark","date":"2024-11-05","arxiv_id":"2411.02733","repositories_listed":1,"syntology":null},{"url":"/paper/unified-triplet-level-hallucination","slug":"unified-triplet-level-hallucination","title":"Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models","date":"2024-10-30","arxiv_id":"2410.23114","repositories_listed":1,"syntology":null},{"url":"/paper/longhalqa-long-context-hallucination","slug":"longhalqa-long-context-hallucination","title":"LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models","date":"2024-10-13","arxiv_id":"2410.09962","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-image-hallucination-in-text-to","slug":"evaluating-image-hallucination-in-text-to","title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","date":"2024-09-19","arxiv_id":"2409.12784","repositories_listed":1,"syntology":null},{"url":"/paper/reefknot-a-comprehensive-benchmark-for","slug":"reefknot-a-comprehensive-benchmark-for","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","date":"2024-08-18","arxiv_id":"2408.09429","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reefknot-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2408.09429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09429"}},"official":{"repos":["JackChen-seu/Reefknot"],"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/enhancing-llm-s-cognition-via-structurization","slug":"enhancing-llm-s-cognition-via-structurization","title":"Enhancing LLM's Cognition via Structurization","date":"2024-07-23","arxiv_id":"2407.16434","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/enhancing-llm-s-cognition-via-structurization#ran","syntology_url":"https://syntology.ai/paper/2407.16434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16434"}},"official":{"repos":["alibaba/struxgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/defan-definitive-answer-dataset-for-llms","slug":"defan-definitive-answer-dataset-for-llms","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","date":"2024-06-13","arxiv_id":"2406.09155","repositories_listed":1,"syntology":null},{"url":"/paper/phd-a-prompted-visual-hallucination","slug":"phd-a-prompted-visual-hallucination","title":"PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset","date":"2024-03-17","arxiv_id":"2403.11116","repositories_listed":1,"syntology":null},{"url":"/paper/diahalu-a-dialogue-level-hallucination","slug":"diahalu-a-dialogue-level-hallucination","title":"DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models","date":"2024-03-01","arxiv_id":"2403.00896","repositories_listed":1,"syntology":null},{"url":"/paper/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"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 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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/truthx-alleviating-hallucinations-by-editing#ran","syntology_url":"https://syntology.ai/paper/2402.17811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17811"}},"official":{"repos":["ictnlp/truthx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-fine-grained-hallucination-by-fine","slug":"mitigating-fine-grained-hallucination-by-fine","title":"Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites","date":"2023-12-04","arxiv_id":"2312.01701","repositories_listed":1,"syntology":null},{"url":"/paper/uhgeval-benchmarking-the-hallucination-of","slug":"uhgeval-benchmarking-the-hallucination-of","title":"UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation","date":"2023-11-26","arxiv_id":"2311.15296","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/uhgeval-benchmarking-the-hallucination-of#ran","syntology_url":"https://syntology.ai/paper/2311.15296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15296"}},"official":{"repos":["IAAR-Shanghai/UHGEval"],"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/hallucidoctor-mitigating-hallucinatory","slug":"hallucidoctor-mitigating-hallucinatory","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","date":"2023-11-22","arxiv_id":"2311.13614","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"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) · 6 unverified","sample_list":"/paper/hallucidoctor-mitigating-hallucinatory#ran","syntology_url":"https://syntology.ai/paper/2311.13614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13614"}},"official":{"repos":["yuqifan1117/hallucidoctor"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/lighter-yet-more-faithful-investigating","slug":"lighter-yet-more-faithful-investigating","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","date":"2023-11-15","arxiv_id":"2311.09335","repositories_listed":1,"syntology":null},{"url":"/paper/an-llm-free-multi-dimensional-benchmark-for","slug":"an-llm-free-multi-dimensional-benchmark-for","title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","date":"2023-11-13","arxiv_id":"2311.07397","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/an-llm-free-multi-dimensional-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2311.07397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07397"}},"official":{"repos":["junyangwang0410/amber"],"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/analyzing-and-mitigating-object-hallucination","slug":"analyzing-and-mitigating-object-hallucination","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","date":"2023-10-01","arxiv_id":"2310.00754","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/analyzing-and-mitigating-object-hallucination#ran","syntology_url":"https://syntology.ai/paper/2310.00754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00754"}},"official":{"repos":["yiyangzhou/lure"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluation-and-analysis-of-hallucination-in","slug":"evaluation-and-analysis-of-hallucination-in","title":"Evaluation and Analysis of Hallucination in Large Vision-Language Models","date":"2023-08-29","arxiv_id":"2308.15126","repositories_listed":1,"syntology":null},{"url":"/paper/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mindmap-knowledge-graph-prompting-sparks#ran","syntology_url":"https://syntology.ai/paper/2308.09729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09729"}},"official":{"repos":["wyl-willing/MindMap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":null,"slug":"hallusegbench-counterfactual-visual-reasoning","title":"HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation","date":"2025-06-26","arxiv_id":"2506.21546","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-image-captioning-hallucinations-in","title":"Mitigating Image Captioning Hallucinations in Vision-Language Models","date":"2025-05-06","arxiv_id":"2505.03420","repositories_listed":0,"syntology":null},{"url":null,"slug":"localizing-before-answering-a-hallucination","title":"Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs","date":"2025-04-30","arxiv_id":"2505.00744","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-evaluation-models-for-rag-who","title":"Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?","date":"2025-03-27","arxiv_id":"2503.21157","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-oriented-preference-alignment-for","title":"Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs","date":"2025-03-26","arxiv_id":"2503.20309","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-in-multimodal-large","title":"Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization","date":"2024-11-15","arxiv_id":"2411.10436","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-hallucination-in-large-visual","title":"A Survey of Hallucination in Large Visual Language Models","date":"2024-10-20","arxiv_id":"2410.15359","repositories_listed":0,"syntology":null},{"url":null,"slug":"tldr-token-level-detective-reward-model-for","title":"TLDR: Token-Level Detective Reward Model for Large Vision Language Models","date":"2024-10-07","arxiv_id":"2410.04734","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectively-enhancing-vision-language-large","title":"Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization","date":"2024-09-22","arxiv_id":"2409.14484","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13612","title":"FIHA: Autonomous Hallucination Evaluation in Vision-Language Models with Davidson Scene Graphs","date":"2024-09-20","arxiv_id":"2409.13612","repositories_listed":0,"syntology":null},{"url":null,"slug":"grapheval-a-knowledge-graph-based-llm","title":"GraphEval: A Knowledge-Graph Based LLM Hallucination Evaluation Framework","date":"2024-07-15","arxiv_id":"2407.10793","repositories_listed":0,"syntology":null},{"url":null,"slug":"lynx-an-open-source-hallucination-evaluation","title":"Lynx: An Open Source Hallucination Evaluation Model","date":"2024-07-11","arxiv_id":"2407.08488","repositories_listed":0,"syntology":null},{"url":null,"slug":"halludial-a-large-scale-benchmark-for","title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","date":"2024-06-11","arxiv_id":"2406.07070","repositories_listed":0,"syntology":null},{"url":null,"slug":"charp-conversation-history-awareness-probing","title":"CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems","date":"2024-05-24","arxiv_id":"2405.15110","repositories_listed":0,"syntology":null},{"url":null,"slug":"textsquare-scaling-up-text-centric-visual","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","date":"2024-04-19","arxiv_id":"2404.12803","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-catch-the-elephant-the-evolvement-of","title":"Can We Catch the Elephant? A Survey of the Evolvement of Hallucination Evaluation on Natural Language Generation","date":"2024-04-18","arxiv_id":"2404.12041","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-and-evaluating-hallucinations-in","title":"Exploring and Evaluating Hallucinations in LLM-Powered Code Generation","date":"2024-04-01","arxiv_id":"2404.00971","repositories_listed":0,"syntology":null},{"url":null,"slug":"hal-eval-a-universal-and-fine-grained","title":"Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models","date":"2024-02-24","arxiv_id":"2402.15721","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-androids-know-they-re-only-dreaming-of","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","date":"2023-12-28","arxiv_id":"2312.17249","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-hallucination-assessment-for","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","date":"2023-10-19","arxiv_id":"2310.12516","repositories_listed":0,"syntology":null}],"syntology_records":14,"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":13,"papers_where_code_ran_first_page":"/task/hallucination-evaluation/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":"ran","page":1,"of":1,"url":"/task/hallucination-evaluation/papers/ran/1","json":"/task/hallucination-evaluation/papers/ran/1.json","rows":13}],"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":"df92db77f10e84b5893bc025b558aa234c3b5bed8efcfb15983fe7bdef10dbd4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}