4 papers
Teach Me After You Learn It: Lookahead Self-Distillation for RLVR
Zepeng Zhai, Meilin Chen
On-policy self-distillation (OPSD) has emerged as a popular training paradigm for LLMs, providing dense, token-level supervision by aligning a model's own distribution with the dis…
SafeRun: Enabling Determinism in LLM Planning for Running
Meilin Chen, Zepeng Zhai, Jiaxuan Zhao +1
Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature. This limitation is especial…
Rewards as Labels: Revisiting RLVR from a Classification Perspective
Zepeng Zhai, Meilin Chen, Jiaxuan Zhao +3
Reinforcement Learning with Verifiable Rewards has recently advanced the capabilities of Large Language Models in complex reasoning tasks by providing explicit rule-based supervisi…
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction
Junlang Qian, Zixiao Zhu, Hanzhang Zhou +3
Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prom…