相关论文: A Critical Evaluation of AI Feedback for Aligning …

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…

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that…

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…

Vision-Language-Action (VLA) models have demonstrated significant potential for generalist robotic policies; however, they struggle to generalize to long-horizon complex tasks in novel real-world domains due to distribution shifts and the…

Students in introductory physics courses often rely on ineffective strategies, focusing on final answers rather than understanding underlying principles. Integrating scientific argumentation into problem-solving fosters critical thinking…

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…

Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among…

Reinforcement Learning from Human Feedback (RLHF) is central in aligning large language models (LLMs) with human values and expectations. However, the process remains susceptible to governance challenges, including evaluator bias,…

Formative assessment is a cornerstone of effective teaching and learning, providing students with feedback to guide their learning. While there has been an exponential growth in the application of generative AI in scaling various aspects of…

A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning abilities. Two major approaches for instruction…

We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…

Reinforcement learning (RL) post-training is a critical stage in modern language model development, playing a key role in improving alignment and reasoning ability. However, several phenomena remain poorly understood, including the…

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remains unclear. We revisit the common claim that ``SFT memorizes,…

To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. While such dialogue…

Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the alignment of human-AI values, further raising the upper bound…

Language models have seen significant growth in the size of their corpus, leading to notable performance improvements. Yet, there has been limited progress in developing models that handle smaller, more human-like datasets. As part of the…

The alignment of large language models (LLMs) is crucial not only for unlocking their potential in specific tasks but also for ensuring that responses meet human expectations and adhere to safety and ethical principles. Current alignment…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very inconsistently to RL finetuning: some show substantial…

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…