{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/language-models-hallucinate-but-may-excel-at","title":"Language Models Hallucinate, but May Excel at Fact Verification","arxiv_id":"2310.14564","date":"2023-10-23","proceeding":null,"authors":["Jian Guan","Jesse Dodge","David Wadden","Minlie Huang","Hao Peng"],"abstract":"Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently \"hallucinate,\" resulting in non-factual outputs. Our carefully-designed human evaluation substantiates the serious hallucination issue, revealing that even GPT-3.5 produces factual outputs less than 25% of the time. This underscores the importance of fact verifiers in order to measure and incentivize progress. Our systematic investigation affirms that LLMs can be repurposed as effective fact verifiers with strong correlations with human judgments. Surprisingly, FLAN-T5-11B, the least factual generator in our study, performs the best as a fact verifier, even outperforming more capable LLMs like GPT3.5 and ChatGPT. Delving deeper, we analyze the reliance of these LLMs on high-quality evidence, as well as their deficiencies in robustness and generalization ability. Our study presents insights for developing trustworthy generation models.","url_abs":"https://arxiv.org/abs/2310.14564v2","url_pdf":"https://arxiv.org/pdf/2310.14564v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"language-models-hallucinate-but-may-excel-at","repo_url":"https://github.com/jianguanthu/llmforfv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fact-verification","task_name":"Fact Verification"},{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.14564","atlas_url":"https://app.syntology.ai/?focus=2310.14564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14564"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jianguanthu/llmforfv","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"74d38464e5b1a718","entry":"acc","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/metric.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"74d38464e5b1a718"}},{"code_sha256_prefix":"ef3019c5908f32d7","entry":"compute_precision_recall_per_threshold","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/meta_evaluation_lib.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/meta_evaluation_lib.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef3019c5908f32d7"}},{"code_sha256_prefix":"241c78299ce539d4","entry":"expected_calibration_error","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/metric.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"241c78299ce539d4"}},{"code_sha256_prefix":"891a0a1f0f9c0727","entry":"get_optimal_gmeans_threshold","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/meta_evaluation_lib.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/meta_evaluation_lib.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"891a0a1f0f9c0727"}},{"code_sha256_prefix":"49f3a8d4ecf2178f","entry":"get_predicted_labels","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/meta_evaluation_lib.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/meta_evaluation_lib.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49f3a8d4ecf2178f"}},{"code_sha256_prefix":"4062d386ad3ef251","entry":"std","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/metric.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4062d386ad3ef251"}},{"code_sha256_prefix":"168cdb58f16242e9","entry":"completion_with_backoff","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/eval_flant5.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/eval_flant5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"168cdb58f16242e9"}},{"code_sha256_prefix":"bc815d8fcd3f6e62","entry":"meta_pro_direct","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/meta_eval.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/meta_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc815d8fcd3f6e62"}},{"code_sha256_prefix":"b2cc9b358b0b170f","entry":"trunct","repo":"jianguanthu/llmforfv","repo_kind":"official","path":"code/eval_flant5.py","file_url":"https://github.com/jianguanthu/llmforfv/blob/HEAD/code/eval_flant5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2cc9b358b0b170f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}