{"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material modified by Syntology; see the attribution page"},"url":"/paper/is-your-llm-outdated-benchmarking-llms","title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","arxiv_id":"2404.08700","date":"2024-04-10","proceeding":null,"authors":["Seyed Mahed Mousavi","Simone Alghisi","Giuseppe Riccardi"],"abstract":"LLMs acquire knowledge from massive data snapshots collected at different timestamps. Their knowledge is then commonly evaluated using static benchmarks. However, factual knowledge is generally subject to time-sensitive changes, and static benchmarks cannot address those cases. We present an approach to dynamically evaluate the knowledge in LLMs and their time-sensitiveness against Wikidata, a publicly available up-to-date knowledge graph. We evaluate the time-sensitive knowledge in twenty-four private and open-source LLMs, as well as the effectiveness of four editing methods in updating the outdated facts. Our results show that 1) outdatedness is a critical problem across state-of-the-art LLMs; 2) LLMs output inconsistent answers when prompted with slight variations of the question prompt; and 3) the performance of the state-of-the-art knowledge editing algorithms is very limited, as they can not reduce the cases of outdatedness and output inconsistency.","url_abs":"https://arxiv.org/abs/2404.08700v3","url_pdf":"https://arxiv.org/pdf/2404.08700v3.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":"is-your-llm-outdated-benchmarking-llms","repo_url":"https://github.com/sislab-unitn/dyknow","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"knowledge-editing","task_name":"knowledge editing"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.08700","atlas_url":"https://app.syntology.ai/?focus=2404.08700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08700"}},"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/sislab-unitn/dyknow","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":12},"by_repo_kind":{"official":{"samples":12,"ran":12,"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":"1bddd74f6ee2e001","entry":"encode_inputs","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"RAG/generate_rag_answers.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/RAG/generate_rag_answers.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":"1bddd74f6ee2e001"}},{"code_sha256_prefix":"17600052c8ca574e","entry":"extract_answer","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/analyze_replies.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/analyze_replies.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":"17600052c8ca574e"}},{"code_sha256_prefix":"1f0f74255167ba0c","entry":"extract_category","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/analyze_replies.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/analyze_replies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f0f74255167ba0c"}},{"code_sha256_prefix":"2ffb6d860fccc774","entry":"extract_target","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_editing/utils.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_editing/utils.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":"2ffb6d860fccc774"}},{"code_sha256_prefix":"c31983832684378f","entry":"generate_answers","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"RAG/generate_rag_answers.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/RAG/generate_rag_answers.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":"c31983832684378f"}},{"code_sha256_prefix":"f48962cb47272ac5","entry":"get_questions","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/utils.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/utils.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":"f48962cb47272ac5"}},{"code_sha256_prefix":"04d2ecf0f938a61e","entry":"is_exception","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_editing/utils.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_editing/utils.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":"04d2ecf0f938a61e"}},{"code_sha256_prefix":"821b26ef3a3a1e9f","entry":"is_exception","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/analyze_replies.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/analyze_replies.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":"821b26ef3a3a1e9f"}},{"code_sha256_prefix":"c5182d6eab527d0c","entry":"load_json","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/utils.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/utils.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":"c5182d6eab527d0c"}},{"code_sha256_prefix":"12ea596f4cbe7637","entry":"prepare_targets","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_editing/utils.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_editing/utils.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":"12ea596f4cbe7637"}},{"code_sha256_prefix":"8734c422f0011297","entry":"questionAnswering","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/models/api.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/models/api.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":"8734c422f0011297"}},{"code_sha256_prefix":"32e0a42879a44343","entry":"write_roman","repo":"sislab-unitn/dyknow","repo_kind":"official","path":"models_output/utils.py","file_url":"https://github.com/sislab-unitn/dyknow/blob/HEAD/models_output/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32e0a42879a44343"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}