Related papers: Self-Generated Critiques Boost Reward Modeling for…

Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on personalized reward models that capture user-specific preferences…

Language Models (LMs) have shown impressive performance in various natural language tasks. However, when it comes to natural language reasoning, LMs still face challenges such as hallucination, generating incorrect intermediate reasoning…

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable…

Recent developments in LLMs offer new opportunities for assisting authors in improving their work. In this paper, we envision a use case where authors can receive LLM-generated reviews that uncover weak points in the current draft. While…

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it…

Retrieval-augmented generation (RAG) improves knowledge-intensive question answering by incorporating external evidence. However, existing RAG methods still suffer from hallucinations and subtle reasoning errors. Recent studies introduce…

Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce…

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

Multimodal large language models (MLLMs) have rapidly advanced from perception tasks to complex multi-step reasoning, yet reinforcement learning with verifiable rewards (RLVR) often leads to spurious reasoning since only the final-answer…

Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert…

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the…

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing line of work on RL with textual feedback, where a critic model…

Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are beneficial-many are…

Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have explored human-like problem-solving strategies, such as…

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses,…