{"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/easy-problems-that-llms-get-wrong","title":"Easy Problems That LLMs Get Wrong","arxiv_id":"2405.19616","date":"2024-05-30","proceeding":null,"authors":["Sean Williams","James Huckle"],"abstract":"We introduce a comprehensive Linguistic Benchmark designed to evaluate the limitations of Large Language Models (LLMs) in domains such as logical reasoning, spatial intelligence, and linguistic understanding, among others. Through a series of straightforward questions, it uncovers the significant limitations of well-regarded models to perform tasks that humans manage with ease. It also highlights the potential of prompt engineering to mitigate some errors and underscores the necessity for better training methodologies. Our findings stress the importance of grounding LLMs with human reasoning and common sense, emphasising the need for human-in-the-loop for enterprise applications. We hope this work paves the way for future research to enhance the usefulness and reliability of new models.","url_abs":"https://arxiv.org/abs/2405.19616v2","url_pdf":"https://arxiv.org/pdf/2405.19616v2.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":"easy-problems-that-llms-get-wrong","repo_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"}],"methods":[],"datasets_introduced":[{"slug":"linguistic-benchmark","name":"Linguistic Benchmark","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.19616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19616"}},"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/autogenai/easy-problems-that-llms-get-wrong","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"3f1a36685687340a","entry":"anthropic_message_parse","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"llm_service.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/llm_service.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f1a36685687340a"}},{"code_sha256_prefix":"6178b88b3ab2e043","entry":"construct_hotz_reflection_question","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"hotz_reflection.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/hotz_reflection.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6178b88b3ab2e043"}},{"code_sha256_prefix":"9e97a16e266c86bd","entry":"construct_multiple_choice_question","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"multiple_choice.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/multiple_choice.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e97a16e266c86bd"}},{"code_sha256_prefix":"22bf823a7e6452df","entry":"create_eval_prompt","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"auto_eval.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/auto_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22bf823a7e6452df"}},{"code_sha256_prefix":"b2a08e455f000e4c","entry":"create_performance_chart","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"charting.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/charting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2a08e455f000e4c"}},{"code_sha256_prefix":"cb2302b85ff5a2ab","entry":"define_data","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"charting.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/charting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb2302b85ff5a2ab"}},{"code_sha256_prefix":"b87033b411752aff","entry":"extract_valid_json","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"auto_eval.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/auto_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b87033b411752aff"}},{"code_sha256_prefix":"7bfe788fa50d7c8d","entry":"google_message_parse","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"llm_service.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/llm_service.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7bfe788fa50d7c8d"}},{"code_sha256_prefix":"5bbc1c34ac330602","entry":"model_clean","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"utils.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5bbc1c34ac330602"}},{"code_sha256_prefix":"52a724e44a628b8b","entry":"openai_message_parse","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"llm_service.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/llm_service.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52a724e44a628b8b"}},{"code_sha256_prefix":"3ea1a7ff2b22ec29","entry":"create_all_llm_eval_messages","repo":"autogenai/easy-problems-that-llms-get-wrong","repo_kind":"official","path":"auto_eval.py","file_url":"https://github.com/autogenai/easy-problems-that-llms-get-wrong/blob/HEAD/auto_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ea1a7ff2b22ec29"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}