{"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/llm-internal-states-reveal-hallucination-risk","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","arxiv_id":"2407.03282","date":"2024-07-03","proceeding":null,"authors":["Ziwei Ji","Delong Chen","Etsuko Ishii","Samuel Cahyawijaya","Yejin Bang","Bryan Wilie","Pascale Fung"],"abstract":"The hallucination problem of Large Language Models (LLMs) significantly limits their reliability and trustworthiness. Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. Inspired by this, our paper investigates whether LLMs can estimate their own hallucination risk before response generation. We analyze the internal mechanisms of LLMs broadly both in terms of training data sources and across 15 diverse Natural Language Generation (NLG) tasks, spanning over 700 datasets. Our empirical analysis reveals two key insights: (1) LLM internal states indicate whether they have seen the query in training data or not; and (2) LLM internal states show they are likely to hallucinate or not regarding the query. Our study explores particular neurons, activation layers, and tokens that play a crucial role in the LLM perception of uncertainty and hallucination risk. By a probing estimator, we leverage LLM self-assessment, achieving an average hallucination estimation accuracy of 84.32\\% at run time.","url_abs":"https://arxiv.org/abs/2407.03282v2","url_pdf":"https://arxiv.org/pdf/2407.03282v2.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":"llm-internal-states-reveal-hallucination-risk","repo_url":"https://github.com/ziweiji/Internal_States_Reveal_Hallucination","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2407.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03282"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ziweiji/Internal_States_Reveal_Hallucination","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"3ffbbeebd9c6703a","entry":"init_out_files","repo":"ziweiji/Internal_States_Reveal_Hallucination","repo_kind":"official","path":"generate/generate_answer.py","file_url":"https://github.com/ziweiji/Internal_States_Reveal_Hallucination/blob/HEAD/generate/generate_answer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ffbbeebd9c6703a"}},{"code_sha256_prefix":"14cc539e921d807f","entry":"get_batch_hidden_states","repo":"ziweiji/Internal_States_Reveal_Hallucination","repo_kind":"official","path":"generate/save_hidden_states.py","file_url":"https://github.com/ziweiji/Internal_States_Reveal_Hallucination/blob/HEAD/generate/save_hidden_states.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":"14cc539e921d807f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}