activity
20212026
most citedFormalizing Generalization and Robustness of Neural Networks to Weight Perturbations

6 citations · 16 across the 13 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs

Yu-An Lu, Ci-Yang Tsai, Yu-Lin Tsai +2

Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help d…