一作ACL 2026Findings· Findings of ACL
Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLM s Reasoning Chains
Seunghyun Park · Yuanyuan Lei
摘要
While LLMs demonstrate impressive reasoning capabilities, they remain fragile in multi-step logic deduction, where a single transition error can propagate through the entire reasoning chain, leading to unstable performance. In this work, we identify logical connectives as primary points of this s...