{"ID":2840350,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.12963","arxiv_id":"2511.12963","title":"MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning","abstract":"We study how to impose domain-consistent structure on large language models (LLMs) used for scientific reasoning and early-stage drug discovery. We present MedRule-KG, a compact knowledge-graph scaffold paired with a lightweight verifier that steers generation toward mathematically and biomedically valid outputs. The system injects curated symbolic facts into prompts and then enforces rule satisfaction with a deterministic checker. We formalize generation as constrained inference, introduce a soft guidance surrogate suitable for decoding, and perform a thorough statistical analysis with uncertainty quantification. Across 90 tasks spanning reaction feasibility, metabolic compatibility, and toxicity screening, MedRule-KG reduces violation counts by 83.2\\% relative to a strong chain-of-thought baseline while improving exact match. Results remain stable under stratification and scale with dataset size, and the verifier adds negligible latency, making the approach practical for interactive design.","short_abstract":"We study how to impose domain-consistent structure on large language models (LLMs) used for scientific reasoning and early-stage drug discovery. We present MedRule-KG, a compact knowledge-graph scaffold paired with a lightweight verifier that steers generation toward mathematically and biomedically valid outputs. The s...","url_abs":"https://arxiv.org/abs/2511.12963","url_pdf":"https://arxiv.org/pdf/2511.12963v2","authors":"[\"Crystal Su\"]","published":"2025-11-17T04:42:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}