跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+64已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 04:33 — 2026-11-17 04:33(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 21:56库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,922 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v3arXiv:2605.27996

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Max Lamparth, Daniel Fein, Andreas Haupt, Marcel Hussing, Mykel J. Kochenderfer

原文摘要

Single-axis mitigations of reward-model biases, such as reducing proxy reliance on length, sycophancy, or style, can redirect optimization pressure onto correlated proxies rather than eliminate it, a new type of reward hacking we call reward bias substitution. The failure is enabled by a measurement-versus-optimization gap between mitigation evaluation on the audit distribution and policy training on the policy-induced distribution. Prior reward-hacking analyses assume a fixed reward proxy, whereas we study the mitigation operator that removes one bias from it, the basic step of iterative reward refinement. We formalize mitigation outcomes into a regime taxonomy and prove that successful mitigation, bias substitution, and overcorrection can produce identical observables under every audit-distribution score, including ranking accuracy and win-rate, even when granted oracle access to the true reward. Across 30 published preference-learning mitigation works, no method we survey reports the evidence needed to certify successful mitigation. Augmenting evaluation with policy-induced distributions while tracking multiple biases provably resolves this distributional gap, and we translate this into actionable prescriptions for mitigation methods and benchmarks. We demonstrate bias substitution in RLHF, where a length penalty in GRPO shortens responses as intended yet makes the policy overconfident and less accurate on open-ended questions, show that the same distributional gap hides failures of published mitigations, and find the necessary preconditions for reward bias substitution documented in published results and in our study of length-sycophancy coupling in LLM responses.

cs.AI