EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms
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 prim...
| Authors | Guilin Zhang, Chuanyi Sun, Kai Zhao et al. |
|---|---|
| Primary category | cs.LG |
| Published | 2 June 2026 |
| Last updated at source | 14 June 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.