做RLHF对齐的团队终于有了处理偏好多样性的实用方案——无需重新训练就能适应新人群，做AI安全或个性化推荐的开发者值得关注。
传统RLHF依赖静态奖励模型，但人类偏好多样且异构，单一模型难以泛化到未见领域。现有多奖励框架局限于固定领域，无法适应新偏好分布。本文提出In-Context Reward Adaptation，一种基于Transformer的框架，通过上下文学习从少量偏好演示中自适应推断奖励结构。研究发现标准Transformer存在渐近偏差，而引入人类响应时间作为辅助信号可成功适应未见领域偏好。该方法为偏好建模提供了更鲁棒的基础，支持异构奖励和偏好分布偏移，是实现灵活人机对齐的可扩展路径。
In-Context Reward Adaptation for Robust Preference Modeling
Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model often lacks the robustness required to generalize to unseen preference domains. While existing multi-reward frameworks attempt to address this, they are often restricted to a fixed set of known domains and fail to adapt to unseen human distributions without costly retraining. In this work, we propose In-Context Reward Adaptation, a transformer-based framework designed to model diverse and unseen human preferences on the fly. By leveraging the in-context learning capabilities of transformers, our approach adaptively infers the underlying reward structure from a small set of preference demonstrations. We demonstrate that while a standard transformer architecture is insufficient for this task by characterizing an asymptotic bias to the ground-truth, incorporating human response time as an auxiliary input signal enables the model to successfully adapt to preferences from previously unseen domains. Our findings show that this approach provides a more robust foundation for preference modeling, allowing for the representation of heterogeneous rewards and preference distribution shift, and offering a scalable path toward more flexible human-AI alignment.