一作ACL 2026Findings· Findings of ACL
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
Van Yang · Shouren Wang · Debargha Ganguly · Xinpeng Li · Chaoda Song · Vikash Singh · Vipin Chaudhary · Xiaotian Han
摘要
Reasoning language models are controlled through explicit modes such as Think and No-think, yet we find that these behaviors are largely governed by a few token-level triggers rather than high-level instructions. Through attention analysis and controlled prompting experiments, we show that a lead...