LLM-driven sequential recommendation formulates next-item prediction as autoregressive generation conditioned on natural-language prompts. However, minor wording changes in semantically equivalent prompts can cause substantial performance fluctuations, undermining robustness and requiring costly manual prompt engineeri...
Xiao-Lin Zheng, Qi-Yong Zhong, Jia-Jie Su et al.· 0 citations
On-policy distillation (OPD) is increasingly applied to frontier foundation model post-training. Prior work in this area has largely focused on algorithmic advances, yet it remains unclear how much OPD depends on its training questions and, in particular, how far this dependence can be reduced. Across two representativ...
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· 0 citations
Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on prompting or supervised fine-tuning, limiting their ability to adapt to unseen trajectories and changing policy contexts. We propose RePolicy, an...
Hou-Cheng Jiang, Bo-Xuan Zhang, Qi-Yong Zhong et al.· 0 citations
MAS-OPD is presented, where Role-Advantage Specialization defines the role advantage as the difference between the teacher signals under target and non-target role conditions, and Privileged Attribution for Coordination attributes an interaction conflict to its source and supplies it to the teacher alone as privileged...
Qi-Yong Zhong, Mao Zheng, Ming-Yang Song et al.· 0 citations
USA is proposed, which converts per-parameter update magnitudes measured during a brief warm-up into per-coordinate perturbation radii, reducing curvature precisely on the coordinates that carry most of the merging displacement.
Qi-Yong Zhong, Mao Zheng, Ming-Yang Song et al.· 1 citation
Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero is proposed.
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· arXiv.org· 24 citations· ⚡3
DF-OPD matches and even surpasses real data, and the questions it produces track the teacher's own post-training data on three key diagnostics of training dynamics, which other real datasets do not.
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· 1 citation
Experiments on reasoning, code-generation, scientific-knowledge, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles.
Jie Sun, Mao Zheng, Mingyang Song et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
