Related papers: LLM Critics Help Catch LLM Bugs

Large language models (LLMs) have emerged as versatile tools in various daily applications. However, they are fraught with issues that undermine their utility and trustworthiness. These include the incorporation of erroneous references…

Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this…

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a discussion. Comparing human to LLM-generated edits, however, we observe a mismatch in…

The increasing use of Large Language Models (LLMs) in software development has garnered significant attention from researchers evaluating the capabilities and limitations of LLMs for code generation. However, much of the research focuses on…

We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries…

Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding…

Large language models (LLMs) increasingly operate in environments where they encounter social information such as other agents' answers, tool outputs, or human recommendations. In humans, such inputs influence judgments in ways that depend…

Recent studies show that instruction tuning (IT) and reinforcement learning from human feedback (RLHF) improve the abilities of large language models (LMs) dramatically. While these tuning methods can help align models with human objectives…

Large Language Models (LLMs) can generate code, but can they generate fast code for complex, real-world software systems? In this study, we investigate this question using a dataset of 65 tasks mined from performance-critical open-source…

Code refactoring is a fundamental software engineering practice aimed at improving code quality and maintainability. Despite its importance, developers often neglect refactoring due to the significant time, effort, and resources it…

Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, these models are trained using next-token prediction, which ignores the syntax and semantics of code. We propose…

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…

Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs. However, current approaches mainly involve basic prompts for intuitive instance-level feedback, which resembles System-1 processes and limits the…

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…

In this paper, we study how well humans can detect text generated by commercial LLMs (GPT-4o, Claude, o1). We hire annotators to read 300 non-fiction English articles, label them as either human-written or AI-generated, and provide…

Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges,…

Large Language Models (LLMs) have shown remarkable capabilities in natural language processing, mathematical problem solving, and tasks related to program synthesis. However, their effectiveness in long-term planning and higher-order…

Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely…

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. However, existing MLLMs prevalently suffer from serious hallucination problems, generating…