Related papers: ENCORE: Entropy-guided Reward Composition for Mult…
Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and…
Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable, such binary feedback is brittle--many tasks admit partially…
Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…
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…
Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet they are often vulnerable to reward hacking due to noisy annotations and systematic biases…
Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been…
Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often…
Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap…
Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…
Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…
Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing…
Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…
Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…
Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this paper, we use entropy to measure a model's uncertainty, i.e.…
Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement learning from human feedback (RLHF). We present a rigorous…
Reward models are critical in techniques like Reinforcement Learning from Human Feedback (RLHF) and Inference Scaling Laws, where they guide language model alignment and select optimal responses. Despite their importance, existing reward…
This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the…
Reinforcement Learning with Verifiable Rewards (RLVR) serves as a cornerstone technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, its training is often plagued by \emph{entropy collapse}, a rapid…
With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness…
Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…