Related papers: Coffee-Gym: An Environment for Evaluating and Impr…

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g.,…

State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement…

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

Large language models (LMs), while powerful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user. Our approach pairs an…

Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In…

Ever since the emergence of large language models (LLMs) and related applications, such as ChatGPT, its performance and error analysis for programming tasks have been subject to research. In this work-in-progress paper, we explore the…

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…

Reinforcement learning (RL) has been widely applied to game-playing and surpassed the best human-level performance in many domains, yet there are few use-cases in industrial or commercial settings. We introduce OR-Gym, an open-source…

Understanding the long-term impact of algorithmic interventions on society is vital to achieving responsible AI. Traditional evaluation strategies often fall short due to the complex, adaptive and dynamic nature of society. While…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

While there is rapid progress in video-LLMs with advanced reasoning capabilities, prior work shows that these models struggle on the challenging task of sports feedback generation and require expensive and difficult-to-collect finetuning…

Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the…

Code review is an important practice in software development, yet it is time-consuming and requires substantial effort. While open-source datasets have been used to train neural models for automating code review tasks, including review…

Code review is essential for maintaining software quality but often time-consuming and cognitively demanding, especially in industrial environments. Recent advancements in language models (LMs) have opened new avenues for automating core…

Code generation has largely improved development efficiency in the era of large language models (LLMs). With the ability to follow instructions, current LLMs can be prompted to generate code solutions given detailed descriptions in natural…

Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality…

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

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…

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of…