Oops, Wait: Token-Level Signals as a Lens into LLM Reasoning

Jaehui Hwang, Dongyoon Han, Sangdoo Yun, Byeongho Heo

Abstract: The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training strategies and model scales remain lacking. In this paper, we analyze token-level signals through token probabilities across various models. We find that specific tokens strongly correlate with reasoning correctness, varying with training strategies while remaining stable across model scales. A closer look at the "wait" token in relation to answer probability demonstrates that models fine-tuned on small-scale datasets acquire reasoning ability through such signals but exploit them only partially. This work provides a systematic lens to observe and understand the dynamics of LLM reasoning.

External IDs:dblp:journals/corr/abs-2601-17421