{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/achieving-97-on-gsm8k-deeply-understanding","title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","arxiv_id":"2404.14963","date":"2024-04-23","proceeding":null,"authors":["Qihuang Zhong","Kang Wang","Ziyang Xu","Juhua Liu","Liang Ding","Bo Du"],"abstract":"Chain-of-Thought (CoT) prompting has enhanced the performance of Large Language Models (LLMs) across various reasoning tasks. However, CoT still falls short in dealing with complex math word problems, as it usually suffers from three pitfalls: semantic misunderstanding errors, calculation errors, and step-missing errors. Prior studies involve addressing the calculation errors and step-missing errors, but neglect the semantic misunderstanding errors, which is the major factor limiting the reasoning performance of LLMs. To this end, we propose a simple-yet-effective method, namely Deeply Understanding the Problems (DUP), to improve the LLMs' math problem-solving ability by addressing semantic misunderstanding errors. The core of our method is to encourage the LLMs to deeply understand the problems and extract the key problem-solving information used for better reasoning. Extensive experiments on 10 diverse reasoning benchmarks show that our DUP method consistently outperforms the other counterparts by a large margin. More encouragingly, DUP achieves a new SOTA result on the GSM8K benchmark, with an accuracy of 97.1% under the zero-shot setting.","url_abs":"https://arxiv.org/abs/2404.14963v5","url_pdf":"https://arxiv.org/pdf/2404.14963v5.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":"achieving-97-on-gsm8k-deeply-understanding","repo_url":"https://github.com/whu-zqh/dup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"DUP prompt upon GPT-4","rank_in_archive_order":2,"of":164,"metrics":{"Accuracy":"97.1"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","task":"Math Word Problem Solving","dataset":"SVAMP","model":"GPT-4 DUP","rank_in_archive_order":26,"of":26,"metrics":{"Accuracy":"94.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.14963","atlas_url":"https://app.syntology.ai/?focus=2404.14963","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2404.14963"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.14963\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.14963"},"call":"get_concepts_for_paper(arxiv_id=\"2404.14963\")"}],"by_repo":[{"repo":"whu-zqh/dup","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"22b2c1250bea77e849fdb17fa3aa020a97aedaaa9f3c15e27805594d3b6f865f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}