{"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/learning-multi-step-reasoning-from-arithmetic","title":"Learning Multi-Step Reasoning by Solving Arithmetic Tasks","arxiv_id":"2306.01707","date":"2023-06-02","proceeding":null,"authors":["Tianduo Wang","Wei Lu"],"abstract":"Mathematical reasoning is regarded as a necessary ability for Language Models (LMs). Recent works demonstrate large LMs' impressive performance in solving math problems. The success is attributed to their Chain-of-Thought (CoT) reasoning abilities, i.e., the ability to decompose complex questions into step-by-step reasoning chains, but such ability seems only to emerge from models with abundant parameters. This work investigates how to incorporate relatively small LMs with the capabilities of multi-step reasoning. We propose to inject such abilities by continually pre-training LMs on a synthetic dataset MsAT which is composed of Multi-step Arithmetic Tasks. Our experiments on four math word problem datasets show the effectiveness of the proposed method in enhancing LMs' math reasoning abilities.","url_abs":"https://arxiv.org/abs/2306.01707v3","url_pdf":"https://arxiv.org/pdf/2306.01707v3.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":"learning-multi-step-reasoning-from-arithmetic","repo_url":"https://github.com/TianduoWang/MsAT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/math-word-problem-solving-on-mawps","task":"Math Word Problem Solving","dataset":"MAWPS","model":"MsAT-DeductReasoner","rank_in_archive_order":2,"of":25,"metrics":{"Accuracy (%)":"94.3"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","task":"Math Word Problem Solving","dataset":"SVAMP","model":"MsAT-DeductReasoner","rank_in_archive_order":18,"of":26,"metrics":{"Execution Accuracy":"48.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.01707","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}