Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL
arXiv:2509.09177v1 Announce Type: cross Abstract: We propose FSPO (Fair Sequence Policy Optimization), a sequence-level reinforcement learning method for LLMs that enforces length-fair clipping directly in the importance-sampling (IS) weight space. We revisit sequence-level RL methods and identify a mismatch when…
