作者位次 #2/7ACL 2026Poster· Natural Language Processing
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding
Fan Liu · Yanhao Wang · Min Zhang · Zhikang Chen · Zeyuan Li · Lewei He · Jiahui Pan
摘要
This paper proposes shortcut decoding, an efficient framework for accelerating Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs). Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. Motivated by the observation that LLMs fr...