{"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/enhancing-reasoning-capabilities-of-llms-via","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","arxiv_id":"2411.12498","date":"2024-11-19","proceeding":null,"authors":["Terufumi Morishita","Gaku Morio","Atsuki Yamaguchi","Yasuhiro Sogawa"],"abstract":"Large language models (LLMs) are capable of solving a wide range of tasks, yet they have struggled with reasoning. To address this, we propose $\\textbf{Additional Logic Training (ALT)}$, which aims to enhance LLMs' reasoning capabilities by program-generated logical reasoning samples. We first establish principles for designing high-quality samples by integrating symbolic logic theory and previous empirical insights. Then, based on these principles, we construct a synthetic corpus named $\\textbf{Formal Logic Deduction Diverse}$ ($\\textbf{FLD}$$_{\\times 2}$), comprising numerous samples of multi-step deduction with unknown facts, diverse reasoning rules, diverse linguistic expressions, and challenging distractors. Finally, we empirically show that ALT on FLD$_{\\times2}$ substantially enhances the reasoning capabilities of state-of-the-art LLMs, including LLaMA-3.1-70B. Improvements include gains of up to 30 points on logical reasoning benchmarks, up to 10 points on math and coding benchmarks, and 5 points on the benchmark suite BBH.","url_abs":"https://arxiv.org/abs/2411.12498v2","url_pdf":"https://arxiv.org/pdf/2411.12498v2.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":"enhancing-reasoning-capabilities-of-llms-via","repo_url":"https://github.com/hitachi-nlp/fld","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enhancing-reasoning-capabilities-of-llms-via","repo_url":"https://github.com/hitachi-nlp/fld-corpus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"tasks":[{"task_slug":"formal-logic","task_name":"Formal Logic"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.12498","atlas_url":"https://app.syntology.ai/?focus=2411.12498","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}