Related papers: reward-lens: A Mechanistic Interpretability Librar…

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

As large language models (LLMs) increasingly interact with external tools, reward modeling for tool use has emerged as a critical yet underexplored area of research. Existing reward models, trained primarily on natural language outputs,…

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

As Large Language Models (LLMs) become increasingly powerful and accessible to human users, ensuring fairness across diverse demographic groups, i.e., group fairness, is a critical ethical concern. However, current fairness and bias…

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and…

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Reward Models (RMs) are crucial to aligning large language models (LLMs), but the degree to which an RM specialized to one task (e.g. writing) generalizes to new tasks (e.g. math) is often not known a priori, often making using only one…

Modern large language models (LLMs) are optimized for human-aligned responses using Reinforcement Learning from Human Feedback (RLHF). However, existing RLHF approaches assume a universal preference model and fail to account for individual…

Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the…

Advancements in Natural Language Processing (NLP), have led to the emergence of Large Language Models (LLMs) such as GPT, Llama, Claude, and Gemini, which excel across a range of tasks but require extensive fine-tuning to align their…

With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have…

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based…

We study how well large language models (LLMs) explain their generations through rationales -- a set of tokens extracted from the input text that reflect the decision-making process of LLMs. Specifically, we systematically study rationales…

A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We study two closely related problems that arise in this…

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…

Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or toy settings, leaving their behavior on commonly used benchmarks underexplored. To address…

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…