{"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/papers/ran/1","list_of":"/task/hallucination-evaluation","task":"Hallucination Evaluation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,13],"of":13,"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"},"first_page":"/task/hallucination-evaluation/papers/ran/1","prev":null,"next":null,"papers":[{"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/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/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":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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/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":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/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":5,"n_unverified":2,"ran_from_kinds":["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/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/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":7,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"7 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; 0 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":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"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/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/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/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":"/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"]}}}],"record_sha256":"28810c9c1a87e463e7961fee51fde26e248209d6c1b050972d89fba68f4ee61d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}