cs.LGNov 2, 2026

Forecasting How RLHF Responds to Reward-Model Edits Before Training

Authors: Zixiao Wang, Duzhen Zhang, Xingbo Du, Dongxia Wu, Le Song

Organizations: Mohamed bin Zayed University of Artificial Intelligence

Abstract

Responses with headers, lists and greater length receive high scores from reward models (RMs), and RLHF policies learn to produce these features even when true quality does not improve. Practitioners therefore edit their RMs, but they learn whether an edit works only after an RL run. We show that the response of a policy to an RM edit can be forecast before training, from samples of the current policy and the scores of the old and new RM. If we read the RM as a set of prices, the first-order theory of KL-regularized RL implies that each feature moves in proportion to its within-prompt covariance with the change in reward. We implant controlled price changes into retrained RMs under a 2^(4-1) fractional factorial design with a self-distilled placebo, run 54 RL runs from six parent policies, and fix every forecast before the runs. With the covariance predictor, we predict the direction of all 20 changes in supply whose forecast has the same sign at every parent and explain 82% of the standardized change. With counterfactual prices, the classical alternative, we explain 50%. The forecast also holds under GRPO and for real RM upgrades, where we explain 66% out of sample with a coefficient frozen from the factorial runs. For rent, the gap between the proxy reward and a gold reward from stronger judges, we rank RM edits correctly with the same covariance over the first 30 steps (Spearman 0.94). This measures the horizon of the forecast: by step 200, the ranking of the factorial edits reverses under both RLOO and GRPO, while the real upgrades keep their order. When we vary the KL coefficient beta, the initial response does not depend on beta, and the response saturates below the KL equilibrium. In one experiment, the long-run response to a price rise is consistent with an additional implicit regularizer beta_0 of about 0.003 to 0.007.

Figures & tables

Appendix figures & tables30 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 8, 2026

A Unifying Lens on Reward Uncertainty in RLHF

Reinforcement learning from human feedback (RLHF) is bottlenecked by reward hacking, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is pessimism: lowering rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty. We argue that the right object is a distributional reward model p(r∣x,y)p(r\mid x,y). Under either a Bayesian inference or a KL-distributionally robust optimization (KL-DRO) lens, the KL-regularized RLHF objective admits a closed-form effective reward r~(x,y)=±βlog⁡Ep[e±r/β]\tilde r(x,y) = \pmβ\log\mathbb{E}_p[e^{\pm r/β}]. The pessimistic branch unifies the prior heuristics for RM ensemble aggregation: mean aggregation, worst-case optimization (WCO), and uncertainty-weighted optimization (UWO) all emerge as limits or truncations of this single expression. This also clarifies the implicit assumptions of each existing rule.
Oct 14, 2026

Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent

Reward model overoptimization in RLHF is usually described as reward hacking. We recast it as rent-seeking: the policy, a firm, earns reward from a regulator, the proxy reward model, that true quality does not back. The lens turns overoptimization into measurable quantities, namely rent, a capture index and deadweight loss, and into testable predictions from the economics of regulation. In a fixed, version-controlled testbed with three model families, accuracy-matched proxy reward models and two gold reward models, RL turns 41% to 66% of its proxy gain into rent while gold reward plateaus. Rent follows each regulator's prices. Neither proxy verifies facts, but one pays for confident specifics and the other for displays of diligence, so RL policies learn to fabricate details about nonexistent entities (97% to 100% of probes) or to deflect factual questions (67% to 98%). Kinship between policy and regulator adds a fixed premium of about 0.1 standard deviations but gives the policy no extra leverage under optimization. At a fixed expected fine, frequent mild audits beat rare severe ones, and random audits are as efficient per audit as targeted ones. Bringing the bunching estimator of tax economics to RL training, we also find a first sign that policies learn to stay just below a targeted audit's threshold.
Apr 24, 2026

Reward Models Are Secretly Value Functions: Temporally Coherent Reward Modeling

Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and produces models whose token-level outputs are noise. We argue this is a missed opportunity: a well-trained reward model's output at any token should represent the conditional expectation of the final reward given the response so far. We introduce Temporally Coherent Reward Modeling (TCRM), which induces this property via two regularization terms on top of the standard Bradley-Terry loss, with minimizers provably equal to conditional expectations. The regularizers correspond to Monte Carlo and TD value-learning objectives, establishing a direct connection to RL value functions. TCRM requires zero changes to architecture, data, or inference, yet unlocks three capabilities from one principle: interpretable token-level reward trajectories (middle-token pairwise accuracy improved from 50% to 88.9%, final-token accuracy preserved); state-of-the-art PRM performance on ProcessBench (44.9% average F1) among models trained only on outcome data; and unified reward/value modeling in PPO, reducing peak GPU memory by 27% and step time by 19% with matching LLM quality.