{"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/impact-of-co-occurrence-on-factual-knowledge","title":"Impact of Co-occurrence on Factual Knowledge of Large Language Models","arxiv_id":"2310.08256","date":"2023-10-12","proceeding":null,"authors":["Cheongwoong Kang","Jaesik Choi"],"abstract":"Large language models (LLMs) often make factually incorrect responses despite their success in various applications. In this paper, we hypothesize that relying heavily on simple co-occurrence statistics of the pre-training corpora is one of the main factors that cause factual errors. Our results reveal that LLMs are vulnerable to the co-occurrence bias, defined as preferring frequently co-occurred words over the correct answer. Consequently, LLMs struggle to recall facts whose subject and object rarely co-occur in the pre-training dataset although they are seen during finetuning. We show that co-occurrence bias remains despite scaling up model sizes or finetuning. Therefore, we suggest finetuning on a debiased dataset to mitigate the bias by filtering out biased samples whose subject-object co-occurrence count is high. Although debiased finetuning allows LLMs to memorize rare facts in the training set, it is not effective in recalling rare facts unseen during finetuning. Further research in mitigation will help build reliable language models by preventing potential errors. The code is available at \\url{https://github.com/CheongWoong/impact_of_cooccurrence}.","url_abs":"https://arxiv.org/abs/2310.08256v1","url_pdf":"https://arxiv.org/pdf/2310.08256v1.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":"impact-of-co-occurrence-on-factual-knowledge","repo_url":"https://github.com/cheongwoong/impact_of_cooccurrence","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.08256","atlas_url":"https://app.syntology.ai/?focus=2310.08256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08256"}},"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/cheongwoong/impact_of_cooccurrence","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"6b674ce8cc2cbafd","entry":"get_masks_for_baseline","repo":"cheongwoong/impact_of_cooccurrence","repo_kind":"official","path":"src/utils/evaluation.py","file_url":"https://github.com/cheongwoong/impact_of_cooccurrence/blob/HEAD/src/utils/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b674ce8cc2cbafd"}},{"code_sha256_prefix":"1b79f5ed386cf90e","entry":"is_pure_alphanumeric","repo":"cheongwoong/impact_of_cooccurrence","repo_kind":"official","path":"src/data_statistics/precompute/extract_entity_set.py","file_url":"https://github.com/cheongwoong/impact_of_cooccurrence/blob/HEAD/src/data_statistics/precompute/extract_entity_set.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b79f5ed386cf90e"}},{"code_sha256_prefix":"c3a69f7597cbf30f","entry":"postprocess_single_prediction_for_baseline","repo":"cheongwoong/impact_of_cooccurrence","repo_kind":"official","path":"src/utils/evaluation.py","file_url":"https://github.com/cheongwoong/impact_of_cooccurrence/blob/HEAD/src/utils/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3a69f7597cbf30f"}},{"code_sha256_prefix":"91161371fcb17d46","entry":"filtering","repo":"cheongwoong/impact_of_cooccurrence","repo_kind":"official","path":"src/utils/text_processing.py","file_url":"https://github.com/cheongwoong/impact_of_cooccurrence/blob/HEAD/src/utils/text_processing.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":"91161371fcb17d46"}},{"code_sha256_prefix":"bf4d06c6c913353a","entry":"text_normalization_without_lemmatization","repo":"cheongwoong/impact_of_cooccurrence","repo_kind":"official","path":"src/utils/text_processing.py","file_url":"https://github.com/cheongwoong/impact_of_cooccurrence/blob/HEAD/src/utils/text_processing.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":"bf4d06c6c913353a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}