相关论文: Mechanistic Interpretability of Code Correctness i…

Code cloning, the duplication of code fragments, is common in software development. While some reuse aids productivity, excessive cloning hurts maintainability and introduces bugs. Hence, automatic code clone detection is vital. Meanwhile,…

Large language models (LLMs) are increasingly used for high-stakes decision-making, yet existing approaches struggle to reconcile scalability, interpretability, and reproducibility. Black-box models obscure their reasoning, while recent…

Language models encode task-relevant knowledge in internal representations that far exceeds their output performance, but whether mechanistic interpretability methods can bridge this knowledge-action gap has not been systematically tested.…

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…

Writing competitive programming problems is exacting. Authors must: set constraints, input distributions, and edge cases that rule out shortcuts; target specific algorithms (e.g., max-flow, dynamic programming, data structures); and…

Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are…

We propose LangProp, a framework for iteratively optimizing code generated by large language models (LLMs), in both supervised and reinforcement learning settings. While LLMs can generate sensible coding solutions zero-shot, they are often…

Recent advances in Large language models (LLMs) have demonstrated their promising capabilities of generating robot operation code to enable LLM-driven robots. To enhance the reliability of operation code generated by LLMs, corrective…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across their dense hidden states, providing no explicit handle for…

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Large language models (LLMs) have shown great promise for autonomous driving. However, discretizing numbers into tokens limits precise numerical reasoning, fails to reflect the positional significance of digits in the training objective,…

Large Language Models (LLMs) have recently emerged as planners for language-instructed agents, generating sequences of actions to accomplish natural language tasks. However, their reliability remains a challenge, especially in long-horizon…

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor…

Recent progress in large language models (LLMs) for code generation has raised serious concerns about intellectual property protection. Malicious users can exploit LLMs to produce paraphrased versions of proprietary code that closely…

With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have…

Future self-adaptive robots are expected to operate in highly dynamic environments while effectively managing uncertainties. However, identifying the sources and impacts of uncertainties in such robotic systems and defining appropriate…