Saved in:
Bibliographic Details
Main Author: Su, Crystal
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.12963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915671341793280
author Su, Crystal
author_facet Su, Crystal
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12963
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning
Su, Crystal
Artificial Intelligence
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.
title MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2511.12963