EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms 文章

ArXiv CS.AI2026-06-04NEWSen作者: Guilin Zhang, Chuanyi Sun, Shahryar Sarkani, John M. Fossaceca

摘要

arXiv:2606.04145v1 Announce Type: cross Abstract: Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality. As Gao et al. (2023) showed, this proxy diverges from world feedback (downstream eval metrics) under sustained optimization pressure, a phenomenon known as reward overoptimization. Existing platform schedulers ignore this divergence: non-clairvoyant schedulers optimize JCT without any quality signal, SLAQ-style quality-aware schedulers use training loss (a weaker proxy that drops monotonically through hacking), and classical per-job early stopping requires human monitoring and does not free shared GPUs. We propose EvalStop, a composable scheduling primitive that terminates jobs on k consecutive eval-score declines, releases GPUs, preserves the best checkpoint, and delegates to any base scheduler.

相关公司

暂无数据

相关人物

暂无数据