{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"truthfulqa","title":"TruthfulQA: Measuring how models mimic human falsehoods","aliases":["TruthfulQA"],"authors":["Stephanie Lin","Jacob Hilton","Owain Evans"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"benchmark","sourceId":"truthfulqa-publication","attributionSourceId":"truthfulqa-publication-author-source","originalUrl":"https://truthful.ai/papers/truthfulqa/","publicationDate":"2021-09-08","updatedOn":"2026-10-25","areas":[],"scopeNote":{"en":"The main dimension follows the task outcome in the original protocol. Topic relevance is documented in the parent research record; no unreviewed question-level links are inferred.","zh":"主维度依据原协议的任务结果确定。主题关联见研究档案，不推断尚未审阅的问题级关联。"},"protocolIds":["truthfulqa"],"contributions":[{"organizationId":"oxford","role":"research","sourceId":"truthfulqa-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"openai","role":"research","sourceId":"truthfulqa-publication-author-source","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Measures truthful answering on questions designed to elicit common human misconceptions.","zh":"通过易诱发常见人类误解的问题，测量回答的真实性。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[{"label":"Codex","url":"https://openai.com/blog/openai-codex/"}],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":[]},"reading":{"id":"truthfulqa","title":"TruthfulQA: Measuring how models mimic human falsehoods","en":{"question":"Can models avoid repeating familiar human misconceptions?","design":"817 questions across 38 categories target imitative falsehoods, with truthfulness and informativeness evaluated separately.","findings":["The original study’s best model was truthful on 58% versus a 94% human baseline.","The largest models in that historical cohort were generally less truthful."],"interpretation":"NUWA interpretation: this tests robustness to common false beliefs, not whether a model deliberately lies.","limits":"Strong performance does not imply truthfulness in specialized domains; historical model-scale findings should not be generalized to all later models.","decisionRelevance":"Model recommendation: preserve generation cohort and separate truthful uncertainty from informative correctness.","takeaway":"NUWA interpretation: this tests robustness to common false beliefs, not whether a model deliberately lies.","connections":[],"scoring":"Truthfulness and informativeness of generated answers, not intention to lie.","conditions":"817 misconception-targeted questions across 38 categories in the original cohort.","statistics":"The original study’s best model was truthful on 58% versus a 94% human baseline.","usage":"Model recommendation: preserve generation cohort and separate truthful uncertainty from informative correctness."},"zh":{"question":"模型能否避免复述常见人类误解？","design":"38类817题针对模仿性错误，并分别评价真实性与信息量。","findings":["原始研究最佳模型真实率58%，人类94%。","该历史比较组中最大模型通常较不真实。"],"interpretation":"NUWA 解读：这测常见错误信念稳健性，不测故意说谎。","limits":"高分不保证专业领域真实；历史规模结果不能外推所有后续模型。","decisionRelevance":"模型建议：保留模型代际，区分真实的不确定表达与有信息的正确回答。","takeaway":"NUWA 解读：这测常见错误信念稳健性，不测故意说谎。","connections":[],"scoring":"生成回答真实性与信息量，不测说谎意图。","conditions":"原始比较组中38类817道误解针对题。","statistics":"原始研究最佳模型真实率58%，人类94%。","usage":"模型建议：保留模型代际，区分真实的不确定表达与有信息的正确回答。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"truthfulqa-publication-author-source","url":"https://arxiv.org/html/2109.07958","locator":"Abstract","version":"Selected original resource https://arxiv.org/html/2109.07958; sha256:c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d; archived source capture; exact capture time not independently established","artifactSha256":"c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d"},{"sourceId":"truthfulqa-publication-author-source","url":"https://arxiv.org/html/2109.07958","locator":"§2 The TruthfulQA Benchmark","version":"Selected original resource https://arxiv.org/html/2109.07958; sha256:c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d; archived source capture; exact capture time not independently established","artifactSha256":"c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d"},{"sourceId":"truthfulqa-publication-author-source","url":"https://arxiv.org/html/2109.07958","locator":"§4 Results","version":"Selected original resource https://arxiv.org/html/2109.07958; sha256:c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d; archived source capture; exact capture time not independently established","artifactSha256":"c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d"},{"sourceId":"truthfulqa-publication-author-source","url":"https://arxiv.org/html/2109.07958","locator":"§7 Conclusion","version":"Selected original resource https://arxiv.org/html/2109.07958; sha256:c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d; archived source capture; exact capture time not independently established","artifactSha256":"c0181fc915933de5c1d5a93995d17bd531bfbc37639d7dfcf8a5eb6d6fae6f0d"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"fa83efd1d1f61d741464cfefa55357f1958acf3cd0dfd9ccbc1d25734560708f"}},"sources":[{"id":"truthfulqa-publication","title":"TruthfulQA: Measuring how models mimic human falsehoods","url":"https://truthful.ai/papers/truthfulqa/","version":"Source capture 2026-10-25","publicationDate":"2021-09-08","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://truthful.ai/papers/truthfulqa","authors":["Stephanie Lin","Jacob Hilton","Owain Evans"]}]}