{"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/unsupervised-real-time-hallucination","title":"Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models","arxiv_id":"2403.06448","date":"2024-03-11","proceeding":null,"authors":["Weihang Su","Changyue Wang","Qingyao Ai","Yiran Hu","Zhijing Wu","Yujia Zhou","Yiqun Liu"],"abstract":"Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research into detecting and mitigating hallucinations of LLMs. Previous studies have mainly concentrated on post-processing techniques for hallucination detection, which tend to be computationally intensive and limited in effectiveness due to their separation from the LLM's inference process. To overcome these limitations, we introduce MIND, an unsupervised training framework that leverages the internal states of LLMs for real-time hallucination detection without requiring manual annotations. Additionally, we present HELM, a new benchmark for evaluating hallucination detection across multiple LLMs, featuring diverse LLM outputs and the internal states of LLMs during their inference process. Our experiments demonstrate that MIND outperforms existing state-of-the-art methods in hallucination detection.","url_abs":"https://arxiv.org/abs/2403.06448v2","url_pdf":"https://arxiv.org/pdf/2403.06448v2.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":"unsupervised-real-time-hallucination","repo_url":"https://github.com/oneal2000/mind","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-real-time-hallucination","repo_url":"https://github.com/baylor-ai/halludetect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.06448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06448"}},"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/oneal2000/mind","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baylor-ai/halludetect","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"99d8ae575c7f474a","entry":"delete_substrings","repo":"oneal2000/mind","repo_kind":"official","path":"generate_data.py","file_url":"https://github.com/oneal2000/mind/blob/HEAD/generate_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99d8ae575c7f474a"}},{"code_sha256_prefix":"5c941df29640afeb","entry":"find_boundaries","repo":"oneal2000/mind","repo_kind":"official","path":"generate_data.py","file_url":"https://github.com/oneal2000/mind/blob/HEAD/generate_data.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":"5c941df29640afeb"}},{"code_sha256_prefix":"d09fcf2f931e6661","entry":"prompt_chat","repo":"oneal2000/mind","repo_kind":"official","path":"generate_hd.py","file_url":"https://github.com/oneal2000/mind/blob/HEAD/generate_hd.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d09fcf2f931e6661"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}