Related papers: Neuron-Guided Interpretation of Code LLMs: Where, …
Many recent models in software engineering introduced deep neural models based on the Transformer architecture or use transformer-based Pre-trained Language Models (PLM) trained on code. Although these models achieve the state of the arts…
Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning…
Programming languages possess rich semantic information - such as data flow - that is represented by graphs and not available from the surface form of source code. Recent code language models have scaled to billions of parameters, but model…
Large language models (LLMs) can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to…
As large language models (LLMs) become more capable, there is an urgent need for interpretable and transparent tools. Current methods are difficult to implement, and accessible tools to analyze model internals are lacking. To bridge this…
Large Language Models (LLMs) recently demonstrated capabilities for generating source code in common programming languages. Additionally, commercial products such as ChatGPT 4 started to provide code interpreters, allowing for the automatic…
Language and culture are deeply intertwined, yet it has been unclear how and where multilingual large language models encode culture. Here, we build on an established methodology for identifying language-specific neurons to localize and…
Locating neurons that are responsible for final predictions is important for opening the black-box large language models and understanding the inside mechanisms. Previous studies have tried to find mechanisms that operate at the neuron…
Programmers increasingly rely on Large Language Models (LLMs) for code generation. However, misalignment between programmers' goals and generated code complicates the code evaluation process and demands frequent switching between prompt…
Large language models (LLMs) are increasingly applied in multilingual contexts, yet their capacity for consistent, logically grounded alignment across languages remains underexplored. We present a controlled evaluation framework for…
Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal value representations remain opaque despite behavioral…
Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded, rule-based systems…
Language models' (LMs) proficiency in handling deterministic symbolic reasoning and rule-based tasks remains limited due to their dependency implicit learning on textual data. To endow LMs with genuine rule comprehension abilities, we…
Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not…
Human languages differ widely in their forms, each having distinct sounds, scripts, and syntax. Yet, they can all convey similar meaning. Do different languages converge on a shared neural substrate for conceptual meaning? We used language…
Despite substantial efforts, neural network interpretability remains an elusive goal, with previous research failing to provide succinct explanations of most single neurons' impact on the network output. This limitation is due to the…
We have only limited understanding of how and why large language models (LLMs) respond in the ways that they do. Their neural networks have proven challenging to interpret, and we are only beginning to tease out the function of individual…
Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models…
The integration of Large Language Models (LLMs) into safety-critical domains, such as nuclear engineering, necessitates a deep understanding of their internal reasoning processes. This paper presents a novel methodology for interpreting how…
Multimodal Large Language Models (MLLMs) have demonstrated strong performance across a wide range of vision-language tasks, yet their internal processing dynamics remain underexplored. In this work, we introduce a probing framework to…