arXiv:2603.08145v1 Announce Type: cross Abstract: Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward maximization brittle and susceptible to proxy over-optimization. We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**, a retraining-free inference-time method that frames response selection as distributionally robust, risk-sensitive decision making. Given multiple preference samples or scalable disagreement proxies, DARC reranks candidates by maximizing a *KL-robust (entropic)* satisfaction objective, and provides simple deployment controls that cap or penalize the corresponding entropic risk premium relative to the mean, enabling explicit risk budgets without retraining. We provide theoretical characterization linking this decoding rule to principled pessimism and KL-based distributionally robust optimization. Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality under noisy, heterogeneous feedback.

arXiv:2602.19416v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives internalized during RLHF remain opaque, making hacking behaviors difficult to detect or correct. We introduce IR3 (Interpretable Reward Reconstruction and Rectification), a framework that reverse-engineers, interprets, and surgically repairs the implicit objectives driving RLHF-tuned models. We propose Contrastive Inverse Reinforcement Learning (C-IRL), which reconstructs the implicit reward function by contrasting paired responses from post-alignment and baseline policies to explain behavioral shifts during RLHF. We then decompose the reconstructed reward via sparse autoencoders into interpretable features, enabling identification of hacking signatures through contribution analysis. Finally, we propose mitigation strategies - clean reward optimization, adversarial shaping, constrained optimization, and feature-guided distillation - that target problematic features while preserving beneficial alignment. Experiments across multiple reward model configurations show that IR3 achieves 0.89 correlation with ground-truth rewards, identifies hacking features with over 90% precision, and significantly reduces hacking behaviors while maintaining capabilities within 3% of the original model.