Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment

Language model alignment aims to make model behavior reflect desirable properties such as helpfulness, safety, and instruction following. Existing methods draw supervision from expert demonstrations, preference judgments, or verifiable outcomes. Demonstrations typically guide supervised fine-tuning (SFT), while preference judgments and verifiers provide rewards for reinforcement learning (RL). This raises a question: can the demonstrations alone be used to derive an explicit, interpretable reward useful in a post-training pipeline? Motivated by inverse reinforcement learning, we introduce Projected Alignment Reward Estimated from Demonstrations (PARED). PARED learns an explicit reward from expert demonstrations over a small set of response-level features, using a lightweight discriminator that separates demonstrations from the policy's own samples in this feature space. Experiments with inference-time reranking and adversarial on-policy RL show improvements both when starting from a base model without an SFT stage and when further optimizing an SFT-trained model. Additionally, we demonstrate that PARED can be used for contextual alignment, in which a single policy learns to adapt its responses to the preferences of different audiences.

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.

Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptation as alignment objectives and reward targets evolve. Existing theoretical analyses justify these methods as approximations to sampling from distributions optimally tilted toward a given reward model. We extend these techniques by introducing reference-model temperature adjustment, which leads to further generalization of inference-time alignment to ensembles of generative reward models combined as a sharpened logarithmic opinion pool (SLOP). To mitigate reward hacking, we propose an algorithm for calibrating SLOP weight parameters and experimentally demonstrate that it improves robustness while preserving alignment performance.