{"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/helma-a-large-scale-hallucination-evaluation","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","arxiv_id":"2305.11747","date":"2023-05-19","proceeding":null,"authors":["Junyi Li","Xiaoxue Cheng","Wayne Xin Zhao","Jian-Yun Nie","Ji-Rong Wen"],"abstract":"Large language models (LLMs), such as ChatGPT, are prone to generate hallucinations, i.e., content that conflicts with the source or cannot be verified by the factual knowledge. To understand what types of content and to which extent LLMs are apt to hallucinate, we introduce the Hallucination Evaluation benchmark for Large Language Models (HaluEval), a large collection of generated and human-annotated hallucinated samples for evaluating the performance of LLMs in recognizing hallucination. To generate these samples, we propose a ChatGPT-based two-step framework, i.e., sampling-then-filtering. Besides, we also hire some human labelers to annotate the hallucinations in ChatGPT responses. The empirical results suggest that ChatGPT is likely to generate hallucinated content in specific topics by fabricating unverifiable information (i.e., about $19.5\\%$ responses). Moreover, existing LLMs face great challenges in recognizing the hallucinations in texts. However, our experiments also prove that providing external knowledge or adding reasoning steps can help LLMs recognize hallucinations. Our benchmark can be accessed at https://github.com/RUCAIBox/HaluEval.","url_abs":"https://arxiv.org/abs/2305.11747v3","url_pdf":"https://arxiv.org/pdf/2305.11747v3.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":"helma-a-large-scale-hallucination-evaluation","repo_url":"https://github.com/RUCAIBox/HaluEval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"helma-a-large-scale-hallucination-evaluation","repo_url":"https://github.com/rucaibox/helma","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"helma-a-large-scale-hallucination-evaluation","repo_url":"https://github.com/IAAR-Shanghai/UHGEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"hallucination-evaluation","task_name":"Hallucination Evaluation"}],"methods":[],"datasets_introduced":[{"slug":"halueval","name":"HaluEval","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11747"}},"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":"deterministic:regex_extraction","url":"https://github.com/RUCAIBox/HaluEval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rucaibox/helma","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IAAR-Shanghai/UHGEval","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"unverified":9},"by_repo_kind":{"official":{"samples":12,"ran":3,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"295b8779d73be38d","entry":"load_dialog","repo":"RUCAIBox/HaluEval","repo_kind":"official","path":"analysis/analyze.py","file_url":"https://github.com/RUCAIBox/HaluEval/blob/HEAD/analysis/analyze.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"295b8779d73be38d"}},{"code_sha256_prefix":"73f3dd95883037cc","entry":"load_qa","repo":"RUCAIBox/HaluEval","repo_kind":"official","path":"analysis/analyze.py","file_url":"https://github.com/RUCAIBox/HaluEval/blob/HEAD/analysis/analyze.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73f3dd95883037cc"}},{"code_sha256_prefix":"3bd42cb5b14b2cad","entry":"load_summary","repo":"RUCAIBox/HaluEval","repo_kind":"official","path":"analysis/analyze.py","file_url":"https://github.com/RUCAIBox/HaluEval/blob/HEAD/analysis/analyze.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bd42cb5b14b2cad"}},{"code_sha256_prefix":"f698390b537e4d97","entry":"get_dialogue_res","repo":"rucaibox/helma","repo_kind":"official","path":"generation/filtering.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/generation/filtering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f698390b537e4d97"}},{"code_sha256_prefix":"211e2e141467c8dd","entry":"get_dialogue_res","repo":"rucaibox/helma","repo_kind":"official","path":"generation/generate.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/generation/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"211e2e141467c8dd"}},{"code_sha256_prefix":"bf66b0debbe71c7e","entry":"get_dialogue_response","repo":"rucaibox/helma","repo_kind":"official","path":"evaluation/evaluate.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf66b0debbe71c7e"}},{"code_sha256_prefix":"57cf187fae039bc2","entry":"get_qa_res","repo":"rucaibox/helma","repo_kind":"official","path":"generation/filtering.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/generation/filtering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57cf187fae039bc2"}},{"code_sha256_prefix":"409dd3a84718a20b","entry":"get_qa_res","repo":"rucaibox/helma","repo_kind":"official","path":"generation/generate.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/generation/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"409dd3a84718a20b"}},{"code_sha256_prefix":"71b0706abb4deccb","entry":"get_qa_response","repo":"rucaibox/helma","repo_kind":"official","path":"evaluation/evaluate.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71b0706abb4deccb"}},{"code_sha256_prefix":"be0c5c938e7e424c","entry":"get_summarization_res","repo":"rucaibox/helma","repo_kind":"official","path":"generation/filtering.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/generation/filtering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be0c5c938e7e424c"}},{"code_sha256_prefix":"f92a9ea55882aef2","entry":"get_summarization_res","repo":"rucaibox/helma","repo_kind":"official","path":"generation/generate.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/generation/generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f92a9ea55882aef2"}},{"code_sha256_prefix":"b3a67ee5030c2ffe","entry":"num_tokens_from_message","repo":"rucaibox/helma","repo_kind":"official","path":"evaluation/evaluate.py","file_url":"https://github.com/rucaibox/helma/blob/HEAD/evaluation/evaluate.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3a67ee5030c2ffe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}