{"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/truthfulqa/papers/ran/1","list_of":"/task/truthfulqa","task":"TruthfulQA","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":[1,20],"of":20,"counts":{"archive_papers_tagged":80,"with_a_code_link":37,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":80,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":14,"listed_every_run_a_failure_of_syntologys_instrument":6,"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/truthfulqa/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/multi-agent-reinforcement-learning-with-focal","slug":"multi-agent-reinforcement-learning-with-focal","title":"Multi-Agent Reinforcement Learning with Focal Diversity Optimization","date":"2025-02-06","arxiv_id":"2502.04492","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/multi-agent-reinforcement-learning-with-focal#ran","syntology_url":"https://syntology.ai/paper/2502.04492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04492"}},"official":{"repos":["sftekin/rl-focal"],"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/novo-norm-voting-off-hallucinations-with","slug":"novo-norm-voting-off-hallucinations-with","title":"NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models","date":"2024-10-11","arxiv_id":"2410.08970","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/novo-norm-voting-off-hallucinations-with#ran","syntology_url":"https://syntology.ai/paper/2410.08970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08970"}},"official":null}},{"url":"/paper/integrative-decoding-improve-factuality-via","slug":"integrative-decoding-improve-factuality-via","title":"Integrative Decoding: Improve Factuality via Implicit Self-consistency","date":"2024-10-02","arxiv_id":"2410.01556","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/integrative-decoding-improve-factuality-via#ran","syntology_url":"https://syntology.ai/paper/2410.01556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01556"}},"official":{"repos":["yicheng98/integrativedecoding"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/texttt-metabench-a-sparse-benchmark-to","slug":"texttt-metabench-a-sparse-benchmark-to","title":"$\\texttt{metabench}$ -- A Sparse Benchmark to Measure General Ability in Large Language Models","date":"2024-07-04","arxiv_id":"2407.12844","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":9,"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/texttt-metabench-a-sparse-benchmark-to#ran","syntology_url":"https://syntology.ai/paper/2407.12844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12844"}},"official":{"repos":["adkipnis/metabench"],"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/varbench-robust-language-model-benchmarking","slug":"varbench-robust-language-model-benchmarking","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","date":"2024-06-25","arxiv_id":"2406.17681","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/varbench-robust-language-model-benchmarking#ran","syntology_url":"https://syntology.ai/paper/2406.17681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17681"}},"official":{"repos":["qbetterk/VarBench"],"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"]}}},{"url":"/paper/steering-without-side-effects-improving-post","slug":"steering-without-side-effects-improving-post","title":"Steering Without Side Effects: Improving Post-Deployment Control of Language Models","date":"2024-06-21","arxiv_id":"2406.15518","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/steering-without-side-effects-improving-post#ran","syntology_url":"https://syntology.ai/paper/2406.15518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15518"}},"official":{"repos":["asacooperstickland/kl-then-steer"],"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/instruction-tuning-with-loss-over","slug":"instruction-tuning-with-loss-over","title":"Instruction Tuning With Loss Over Instructions","date":"2024-05-23","arxiv_id":"2405.14394","repositories_listed":1,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":20,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/instruction-tuning-with-loss-over#ran","syntology_url":"https://syntology.ai/paper/2405.14394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14394"}},"official":{"repos":["zhengxiangshi/instructionmodelling"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/when-hindsight-is-not-20-20-testing-limits-on","slug":"when-hindsight-is-not-20-20-testing-limits-on","title":"When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models","date":"2024-04-14","arxiv_id":"2404.09129","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-hindsight-is-not-20-20-testing-limits-on#ran","syntology_url":"https://syntology.ai/paper/2404.09129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09129"}},"official":{"repos":["yanhong-lbh/llm-selfreflection-eval"],"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/pollmgraph-unraveling-hallucinations-in-large","slug":"pollmgraph-unraveling-hallucinations-in-large","title":"PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics","date":"2024-04-06","arxiv_id":"2404.04722","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pollmgraph-unraveling-hallucinations-in-large#ran","syntology_url":"https://syntology.ai/paper/2404.04722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04722"}},"official":{"repos":["hitum-dev/pollmgraph"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-sharpness-as-alerts-an-inner","slug":"in-context-sharpness-as-alerts-an-inner","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","date":"2024-03-03","arxiv_id":"2403.01548","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-context-sharpness-as-alerts-an-inner#ran","syntology_url":"https://syntology.ai/paper/2403.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01548"}},"official":{"repos":["hkust-nlp/activation_decoding"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/sage-evaluating-moral-consistency-in-large","slug":"sage-evaluating-moral-consistency-in-large","title":"SaGE: Evaluating Moral Consistency in Large Language Models","date":"2024-02-21","arxiv_id":"2402.13709","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/sage-evaluating-moral-consistency-in-large#ran","syntology_url":"https://syntology.ai/paper/2402.13709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13709"}},"official":{"repos":["vnnm404/SaGE"],"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/tuning-language-models-by-proxy","slug":"tuning-language-models-by-proxy","title":"Tuning Language Models by Proxy","date":"2024-01-16","arxiv_id":"2401.08565","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"9 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tuning-language-models-by-proxy#ran","syntology_url":"https://syntology.ai/paper/2401.08565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08565"}},"official":{"repos":["alisawuffles/proxy-tuning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"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/tool-augmented-reward-modeling","slug":"tool-augmented-reward-modeling","title":"Tool-Augmented Reward Modeling","date":"2023-10-02","arxiv_id":"2310.01045","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tool-augmented-reward-modeling#ran","syntology_url":"https://syntology.ai/paper/2310.01045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01045"}},"official":{"repos":["ernie-research/Tool-Augmented-Reward-Model"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sight-beyond-text-multi-modal-training","slug":"sight-beyond-text-multi-modal-training","title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","date":"2023-09-13","arxiv_id":"2309.07120","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sight-beyond-text-multi-modal-training#ran","syntology_url":"https://syntology.ai/paper/2309.07120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07120"}},"official":{"repos":["ucsc-vlaa/sight-beyond-text"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rain-your-language-models-can-align","slug":"rain-your-language-models-can-align","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","date":"2023-09-13","arxiv_id":"2309.07124","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":0,"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/rain-your-language-models-can-align#ran","syntology_url":"https://syntology.ai/paper/2309.07124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07124"}},"official":{"repos":["SafeAILab/RAIN"],"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/dola-decoding-by-contrasting-layers-improves","slug":"dola-decoding-by-contrasting-layers-improves","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","date":"2023-09-07","arxiv_id":"2309.03883","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dola-decoding-by-contrasting-layers-improves#ran","syntology_url":"https://syntology.ai/paper/2309.03883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03883"}},"official":{"repos":["voidism/dola"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/inference-time-intervention-eliciting","slug":"inference-time-intervention-eliciting","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","date":"2023-06-06","arxiv_id":"2306.03341","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":0,"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/inference-time-intervention-eliciting#ran","syntology_url":"https://syntology.ai/paper/2306.03341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03341"}},"official":{"repos":["likenneth/honest_llama"],"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/truthfulqa-measuring-how-models-mimic-human","slug":"truthfulqa-measuring-how-models-mimic-human","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","date":"2021-09-08","arxiv_id":"2109.07958","repositories_listed":3,"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/truthfulqa-measuring-how-models-mimic-human#ran","syntology_url":"https://syntology.ai/paper/2109.07958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07958"}},"official":{"repos":["sylinrl/truthfulqa"],"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"]}}}],"record_sha256":"d5c41805bd3dc2a882e5087165b75fe64c2b7ef98b2272f7b7b199ff3fd25d06","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}