English
Related papers

Related papers: NeuronScope: A Multi-Agent Framework for Explainin…

200 papers

Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of…

Artificial Intelligence · Computer Science 2025-11-03 Mengjie Deng , Guanting Dong , Zhicheng Dou

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

Computation and Language · Computer Science 2024-12-12 Xufeng Duan , Xinyu Zhou , Bei Xiao , Zhenguang G. Cai

Advances in Large Language Models (LLMs) have led to remarkable capabilities, yet their inner mechanisms remain largely unknown. To understand these models, we need to unravel the functions of individual neurons and their contribution to…

Machine Learning · Computer Science 2023-06-01 Alex Foote , Neel Nanda , Esben Kran , Ioannis Konstas , Shay Cohen , Fazl Barez

Despite advances in embodied AI, agent reasoning systems still struggle to capture the fundamental conceptual structures that humans naturally use to understand and interact with their environment. To address this, we propose a novel…

Artificial Intelligence · Computer Science 2025-04-01 François Olivier , Zied Bouraoui

Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Previous mechanistic descriptions have used individual neurons…

Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs…

Computation and Language · Computer Science 2024-06-07 Tianyi Tang , Wenyang Luo , Haoyang Huang , Dongdong Zhang , Xiaolei Wang , Xin Zhao , Furu Wei , Ji-Rong Wen

The development of artificial intelligence systems capable of understanding and reasoning about complex real-world scenarios is a significant challenge. In this work we present a novel approach to enhance and exploit LLM reactive capability…

Artificial Intelligence · Computer Science 2024-11-20 Stefano De Giorgis , Aldo Gangemi , Alessandro Russo

Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks. However, comprehending the underlying reasons for their effectiveness remains a challenging problem. Interpreting deep neural networks…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Chenxu Zhao , Wei Qian , Yucheng Shi , Mengdi Huai , Ninghao Liu

Large Language Models (LLMs) are playing an increasingly important role in physics research by assisting with symbolic manipulation, numerical computation, and scientific reasoning. However, ensuring the reliability, transparency, and…

Artificial Intelligence · Computer Science 2025-08-19 Yinggan Xu , Hana Kimlee , Yijia Xiao , Di Luo

Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distributed amongst its different components. However, the lack of…

Computation and Language · Computer Science 2023-11-07 Yimin Fan , Fahim Dalvi , Nadir Durrani , Hassan Sajjad

Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large…

Computation and Language · Computer Science 2024-09-19 Priyesh Vakharia , Abigail Kufeldt , Max Meyers , Ian Lane , Leilani Gilpin

Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal,…

Software Engineering · Computer Science 2026-03-20 Zhe Yin , Xiaodong Gu , Beijun Shen

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…

Machine Learning · Computer Science 2023-04-26 Alex Foote , Neel Nanda , Esben Kran , Ionnis Konstas , Fazl Barez

Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research,…

Computation and Language · Computer Science 2025-05-21 Jiahao Huo , Yibo Yan , Boren Hu , Yutao Yue , Xuming Hu

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better…

Computation and Language · Computer Science 2019-11-25 Jian Li , Xing Wang , Baosong Yang , Shuming Shi , Michael R. Lyu , Zhaopeng Tu

Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mechanisms. These investigations are challenging since CNNs…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Robin Hesse , Jonas Fischer , Simone Schaub-Meyer , Stefan Roth

We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation refinement, where an…

Computation and Language · Computer Science 2026-05-05 Arnau Marin-Llobet , Javier Ferrando

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Computation and Language · Computer Science 2026-04-21 Nils Feldhus , Laura Kopf

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

Computation and Language · Computer Science 2026-03-31 Yibo Yang