一作ACL 2026Findings· Findings of ACL
REAP : Towards Effective Training-Free Chemical Reasoning with Explicit Atomic Priors
Mingxu Zhang · Dazhong Shen · Qi Zhang · Ying Sun
摘要
Large Language Models (LLMs) exhibit strong general reasoning but struggle in molecular science due to the lack of explicit priors required for precise chemical reasoning. Current solutions inject priors into parameters, but this static coupling hinders rapid knowledge updates and often compromis...