Shin'ya Yamaguchi

Mitigating Query Shortcuts in Chain-of-Thought with Context-Aware Decoding

While Chain-of-Thought (CoT) prompting improves the reasoning performance of large language models (LLMs), recent studies have shown that final answers do not always depend on the generated rationales. In particular, LLMs may rely on query-specific shortcuts rather than the information provided by their reasoning steps...