Related papers: Information-Theoretic Reward Modeling for Stable R…

In this paper, we propose a novel method, IB-RAR, which uses Information Bottleneck (IB) to strengthen adversarial robustness for both adversarial training and non-adversarial-trained methods. We first use the IB theory to build…

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second,…

Reward models have been increasingly critical for improving the reasoning capability of LLMs. Existing research has shown that a well-trained reward model can substantially improve model performances at inference time via search. However,…

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…

Because it is difficult to precisely specify complex objectives, reinforcement learning policies are often optimized using proxy reward functions that only approximate the true goal. However, optimizing proxy rewards frequently leads to…

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently…

Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. To understand how reward hacking arises, we construct four RL environments with misspecified…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. RL from AI Feedback (RLAIF), introduced in…

Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers and the original optimization objective could…

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…

We study the problem of reinforcement learning from human feedback (RLHF), a critical problem in training large language models, from a theoretical perspective. Our main contribution is the design of novel sample-efficient RLHF algorithms…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

The goal of the Inverse reinforcement learning (IRL) task is to identify the underlying reward function and the corresponding optimal policy from a set of expert demonstrations. While most IRL algorithms' theoretical guarantees rely on a…