一作ACL 2026Poster· Natural Language Processing
Do LLM s Encode Functional Importance of Reasoning Tokens ?
Janvijay Singh · Dilek Hakkani-Tür
摘要
Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate functionally relevant reasoning. Prior work on compact reasoning shortens such chains through probabilistic sampling,...