{"ID":2853308,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16309","arxiv_id":"2510.16309","title":"MedRule-KG: A Knowledge-Graph--Steered Scaffold for Mathematical Reasoning with a Lightweight Verifier","abstract":"Large language models (LLMs) often produce fluent reasoning steps while violating simple mathematical or logical constraints. We introduce MedRule-KG, a compact typed knowledge graph coupled with a symbolic verifier, designed to enforce mathematically interpretable rules in reasoning tasks. MedRule-KG encodes entities, relations, and three domain-inspired rules, while the verifier checks predictions and applies minimal corrections to guarantee consistency. On a 90-example FDA-derived benchmark, grounding in MedRule-KG improves exact match (EM) from 0.767 to 0.900, and adding the verifier yields 1.000 EM while eliminating rule violations entirely. We demonstrate how MedRule-KG provides a general scaffold for safe mathematical reasoning, discuss ablations, and release code and data to encourage reproducibility.","short_abstract":"Large language models (LLMs) often produce fluent reasoning steps while violating simple mathematical or logical constraints. We introduce MedRule-KG, a compact typed knowledge graph coupled with a symbolic verifier, designed to enforce mathematically interpretable rules in reasoning tasks. MedRule-KG encodes entities,...","url_abs":"https://arxiv.org/abs/2510.16309","url_pdf":"https://arxiv.org/pdf/2510.16309v3","authors":"[\"Crystal Su\"]","published":"2025-10-18T02:39:13Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}