{"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/minicheck-efficient-fact-checking-of-llms-on","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","arxiv_id":"2404.10774","date":"2024-04-16","proceeding":null,"authors":["Liyan Tang","Philippe Laban","Greg Durrett"],"abstract":"Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of fact-checking are based on verifying each piece of a model generation against potential evidence using an LLM. However, this process can be very computationally expensive, requiring many calls to a model to check a single response. In this work, we show how to build small fact-checking models that have GPT-4-level performance but for 400x lower cost. We do this by constructing synthetic training data with GPT-4, which involves creating realistic yet challenging instances of factual errors via a structured generation procedure. Training on this data teaches models to check each fact in the claim and recognize synthesis of information across sentences. For evaluation, we unify datasets from recent work on fact-checking and grounding LLM generations into a new benchmark, LLM-AggreFact. Our best system MiniCheck-FT5 (770M parameters) outperforms all systems of comparable size and reaches GPT-4 accuracy. We release LLM-AggreFact, code for data synthesis, and models.","url_abs":"https://arxiv.org/abs/2404.10774v2","url_pdf":"https://arxiv.org/pdf/2404.10774v2.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":"minicheck-efficient-fact-checking-of-llms-on","repo_url":"https://github.com/liyan06/minicheck","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"minicheck-efficient-fact-checking-of-llms-on","repo_url":"https://github.com/vectara/hallucination-leaderboard","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fact-checking-on","task":"Fact Checking","dataset":"^(#$!@#$)(()))******","model":"Abc","rank_in_archive_order":1,"of":1,"metrics":{"0..5sec":"2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.10774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10774"}},"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/liyan06/minicheck","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vectara/hallucination-leaderboard","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Liyan06/MiniCheck","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"f28664b6930ce419","entry":"MiniCheck","repo":"Liyan06/MiniCheck","repo_kind":"official","path":"minicheck/minicheck.py","file_url":"https://github.com/Liyan06/MiniCheck/blob/HEAD/minicheck/minicheck.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f28664b6930ce419"}},{"code_sha256_prefix":"b8617b4254aed28c","entry":"get_permutations_of_facts","repo":"liyan06/minicheck","repo_kind":"official","path":"synthetic_data_gen/D2C_gen.py","file_url":"https://github.com/liyan06/minicheck/blob/HEAD/synthetic_data_gen/D2C_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b8617b4254aed28c"}},{"code_sha256_prefix":"73b4776d89175db5","entry":"Inferencer","repo":"Liyan06/MiniCheck","repo_kind":"official","path":"minicheck/minicheck.py","file_url":"https://github.com/Liyan06/MiniCheck/blob/HEAD/minicheck/minicheck.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73b4776d89175db5"}},{"code_sha256_prefix":"81822f43aa62fd5c","entry":"LLMCheck","repo":"Liyan06/MiniCheck","repo_kind":"official","path":"minicheck/minicheck.py","file_url":"https://github.com/Liyan06/MiniCheck/blob/HEAD/minicheck/minicheck.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81822f43aa62fd5c"}},{"code_sha256_prefix":"166f1ad6d53d618d","entry":"construct_removed_sent_dict_wrapper","repo":"liyan06/minicheck","repo_kind":"official","path":"synthetic_data_gen/C2D_gen.py","file_url":"https://github.com/liyan06/minicheck/blob/HEAD/synthetic_data_gen/C2D_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"166f1ad6d53d618d"}},{"code_sha256_prefix":"06201cbb8367e9c9","entry":"get_response_for_all_chunks","repo":"liyan06/minicheck","repo_kind":"official","path":"synthetic_data_gen/D2C_gen.py","file_url":"https://github.com/liyan06/minicheck/blob/HEAD/synthetic_data_gen/D2C_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"06201cbb8367e9c9"}},{"code_sha256_prefix":"d3facd3508b51062","entry":"sent_tokenize_with_newlines","repo":"Liyan06/MiniCheck","repo_kind":"official","path":"minicheck/minicheck.py","file_url":"https://github.com/Liyan06/MiniCheck/blob/HEAD/minicheck/minicheck.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3facd3508b51062"}},{"code_sha256_prefix":"4cb70b41a391c83d","entry":"split_into_chunks","repo":"liyan06/minicheck","repo_kind":"official","path":"synthetic_data_gen/D2C_gen.py","file_url":"https://github.com/liyan06/minicheck/blob/HEAD/synthetic_data_gen/D2C_gen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb70b41a391c83d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}