Yuqian Fu

The paper demonstrates that the valence structure learned by modern LLMs aligns with human EEG emotional representations, but finds that further supervised alignment is ineffective due to a phenomenon called saturation regularity.

This paper proposes two horizon-control strategies, Progressive OPD (POPD) and Truncated OPD (TOPD), demonstrating that full rollouts are often unnecessary for On-Policy Distillation, leading to significant improvements in training efficiency.