一作ACL 2026Findings· Findings of ACL
From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLM s
Shaojie Wang · Liang Zhang
摘要
Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation, focusing on logical relationship understanding, which is a co...