Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models
Yueqing Hu, Tianhong Wang
Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate questions whether this alignment r…
cs.CL2026
Hán Dān Xué Bù (Mimicry) or Qīng Chū Yú Lán (Mastery)? A Cognitive Perspective on Reasoning Distillation in Large Language Models
Yueqing Hu, Xinyang Peng, Shuting Peng +2
Recent Large Reasoning Models trained via reinforcement learning exhibit a "natural" alignment with human cognitive costs. However, we show that the prevailing paradigm of reasonin…