4 papers
OPSRD: On-Policy Self-Role Distillation
Weijie Ren, Yanwen Zhang, Hao Li +3
Role prompting elicits specialized behavior from large language models through an expert identity, offering a lightweight way to guide reasoning on demanding tasks. However, evalua…
SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration
Weijie Ren, Yanwen Zhang, Hao Li +3
Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couples correction with exposure to…
ReTaCo: Residual-Target Control for On-Policy Distillation
Zixiang Ni, Zhuo Hu, Renjie Cao +8
On-policy distillation (OPD) trains a student on its own generated prefixes with token-level teacher feedback, but transmitting or storing the teacher's full-vocabulary distributio…
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Hao Li, MeiJia Chen, Weijie Ren +4
On-policy distillation (OPD) trains a student to match the teacher's next-token distributions on the student's own trajectories and has yielded substantial empirical gains. General…