Related papers: Neuron-Guided Interpretation of Code LLMs: Where, …

Large language models (LLMs) are the result of a massive experiment in bottom-up, data-driven reverse engineering of language at scale. Despite their utility in a number of downstream NLP tasks, ample research has shown that LLMs are…

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…

Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs process culturally grounded information, we study the presence of culture-sensitive neurons, i.e.,…

Large Language Models (LLMs) have achieved remarkable success in automated code translation. While prior work has focused on improving translation accuracy through advanced prompting and iterative repair, the reliability of the underlying…

Multilingual language models have significantly advanced due to rapid progress in natural language processing. Models like BLOOM 1.7B, trained on diverse multilingual datasets, aim to bridge linguistic gaps. However, their effectiveness in…

While large language models (LLMs) exhibit state-of-the-art performance in various tasks, recent studies have revealed their struggle for code translation. This is because they haven't been extensively pre-trained with parallel multilingual…

As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure the underlying reasoning of generative models, offering…

Code translation aims to convert source code from one programming language (PL) to another. Given the promising abilities of large language models (LLMs) in code synthesis, researchers are exploring their potential to automate code…

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on…

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for…

Despite the remarkable evolution of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. Previous work largely focused on what these models learn at the representation level. We break this…

Large language models that require multiple GPU cards to host are usually the most capable models. It is necessary to understand and steer these models, but the current technologies do not support the interpretability and steering of these…

Understanding the function of individual neurons within language models is essential for mechanistic interpretability research. We propose $\textbf{Neuron to Graph (N2G)}$, a tool which takes a neuron and its dataset examples, and…

Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored. Inspired by Bloom's Taxonomy, we propose a…

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…

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) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…