{"url":"/task/truthfulqa","name":"TruthfulQA","slug":"truthfulqa","description_markdown":null,"categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":80,"papers_with_code":37,"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/knowledge","name":"Knowledge","full_name":"","num_papers_in_archive":3},{"url":"/dataset/genaipabench-dataset","name":"GenAIPABench-Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/news","name":"News","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":37,"tagged_in_all":80,"items":[{"url":"/paper/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_unverified":2,"n_pointer_only":7}},{"url":"/paper/rlhf-workflow-from-reward-modeling-to-online","title":"RLHF Workflow: From Reward Modeling to Online RLHF","date":"2024-05-13","arxiv_id":"2405.07863","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/lacie-listener-aware-finetuning-for","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","date":"2024-05-31","arxiv_id":"2405.21028","repositories_listed":2,"syntology":null},{"url":"/paper/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":8,"n_unverified":2,"n_pointer_only":10}},{"url":"/paper/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":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/red-teaming-large-language-models-using-chain","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","date":"2023-08-18","arxiv_id":"2308.09662","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-elicitation-of-language-models","title":"Unsupervised Elicitation of Language Models","date":"2025-06-11","arxiv_id":"2506.10139","repositories_listed":1,"syntology":null},{"url":"/paper/truth-neurons","title":"Truth Neurons","date":"2025-05-18","arxiv_id":"2505.12182","repositories_listed":1,"syntology":null},{"url":"/paper/delta-a-decoding-strategy-based-on-logit","title":"DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability","date":"2025-03-04","arxiv_id":"2503.02343","repositories_listed":1,"syntology":null},{"url":"/paper/truth-knows-no-language-evaluating","title":"Truth Knows No Language: Evaluating Truthfulness Beyond English","date":"2025-02-13","arxiv_id":"2502.09387","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/chair-classifier-of-hallucination-as-improver","title":"CHAIR -- Classifier of Hallucination as Improver","date":"2025-01-05","arxiv_id":"2501.02518","repositories_listed":1,"syntology":null},{"url":"/paper/whyphi-fine-tuning-phi-3-for-multiple-choice","title":"(WhyPHI) Fine-Tuning PHI-3 for Multiple-Choice Question Answering: Methodology, Results, and Challenges","date":"2025-01-03","arxiv_id":"2501.01588","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/a-test-suite-of-prompt-injection-attacks-for","title":"A test suite of prompt injection attacks for LLM-based machine translation","date":"2024-10-07","arxiv_id":"2410.05047","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":2,"n_pointer_only":3}},{"url":"/paper/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_unverified":1,"n_pointer_only":9}},{"url":"/paper/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_unverified":0,"n_pointer_only":6}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/enhancing-language-model-factuality-via","title":"Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding","date":"2024-06-19","arxiv_id":"2406.13230","repositories_listed":1,"syntology":null},{"url":"/paper/machine-unlearning-in-large-language-models","title":"Machine Unlearning in Large Language Models","date":"2024-05-24","arxiv_id":"2405.15152","repositories_listed":1,"syntology":null},{"url":"/paper/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":12,"n_unverified":8,"n_pointer_only":20}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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_unverified":1,"n_pointer_only":7}},{"url":"/paper/nl-iti-optimizing-probing-and-intervention","title":"Non-Linear Inference Time Intervention: Improving LLM Truthfulness","date":"2024-03-27","arxiv_id":"2403.18680","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":2,"n_pointer_only":4}},{"url":"/paper/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_unverified":1,"n_pointer_only":3}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/truth-forest-toward-multi-scale-truthfulness","title":"Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning","date":"2023-12-29","arxiv_id":"2312.17484","repositories_listed":1,"syntology":null}],"syntology_records":18,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}