paper-with-me

홈 › Papers

MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning

2025-11-17 · Crystal Su arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.12963

Code (0)

등록된 구현이 없습니다.

Tasks

Drug Discovery

Similar Papers 제목 키워드 기반

MedRule-KG: A Knowledge-Graph--Steered Scaffold for Mathematical Reasoning with a Lightweight Verifier

2025-10-18 · Crystal Su arxiv

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, des…

Mathematical Reasoning

Walking on the DARKSIDE

2026-08-24 · Aldo Gangemi, Emanuele Bottazzi arxiv

Large Language Models (LLMs) recognise patterns but do not natively track the path of exclusions that a coherent discourse demands. When an input rests on a fabricated authority, a misapplied mechanism, or a surreptitiou…

MotifBench: A standardized protein design benchmark for motif-scaffolding problems

2025-02-18 · Zhuoqi Zheng, Bo Zhang, Kieran Didi, Kevin K. Yang 외

The motif-scaffolding problem is a central task in computational protein design: Given the coordinates of atoms in a geometry chosen to confer a desired biochemical function (a motif), the task is to identify diverse pro…

Protein DesignProtein Structure Prediction

Scaffold-Induced Molecular Graph (SIMG): Effective Graph Sampling Methods for High-Throughput Computational Drug Discovery

2021-09-10 · Austin Clyde, Ashka Shah, Max Zvyagin, Arvind Ramanathan 외

Scaffold based drug discovery (SBDD) is a technique for drug discovery which pins chemical scaffolds as the framework of design. Scaffolds, or molecular frameworks, organize the design of compounds into local neighborhoo…

Drug DiscoveryGraph Sampling

Scaffold-based molecular design using graph generative model

2019-05-31 · Jaechang Lim, Sang-Yeon Hwang, Seungsu Kim, Seokhyun Moon 외

Searching new molecules in areas like drug discovery often starts from the core structures of candidate molecules to optimize the properties of interest. The way as such has called for a strategy of designing molecules r…

Drug Discoverymodel