English
Related papers

Related papers: Interpretability in the Wild: a Circuit for Indire…

200 papers

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Computation and Language · Computer Science 2026-02-26 Pierre Beckmann , Matthieu Queloz

While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation…

Computation and Language · Computer Science 2026-04-21 Yutong Gao , Qinglin Meng , Yuan Zhou , Liangming Pan

Large Language Models (LLMs) have experienced a rapid rise in AI, changing a wide range of applications with their advanced capabilities. As these models become increasingly integral to decision-making, the need for thorough…

Machine Learning · Computer Science 2024-01-09 Jatin Nainani

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.…

Artificial Intelligence · Computer Science 2026-03-20 Sanjay Basu , Sadiq Y. Patel , Parth Sheth , Bhairavi Muralidharan , Namrata Elamaran , Aakriti Kinra , John Morgan , Rajaie Batniji

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Computation and Language · Computer Science 2025-04-14 Miguel López-Otal , Jorge Gracia , Jordi Bernad , Carlos Bobed , Lucía Pitarch-Ballesteros , Emma Anglés-Herrero

Interpretability research often aims to predict how a model will respond to targeted interventions on specific mechanisms. However, it rarely predicts how a model will respond to unseen input data. This paper explores the promises and…

Machine Learning · Computer Science 2025-07-10 Victoria R. Li , Jenny Kaufmann , Martin Wattenberg , David Alvarez-Melis , Naomi Saphra

Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yubin Wang , Xinyang Jiang , De Cheng , Xiangqian Zhao , Zilong Wang , Dongsheng Li , Cairong Zhao

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Machine Learning · Computer Science 2026-05-12 Ward Gauderis , Thomas Dooms , Steven T. Holmer , Kola Ayonrinde , Geraint A. Wiggins

Research on Large Language Models (LLMs) increasingly focuses on identifying mechanistic explanations for their behaviors, yet the field lacks clear principles for determining when (and how) findings from one model instance generalize to…

Artificial Intelligence · Computer Science 2025-09-30 Sean Trott

Free-text explanations are expressive and easy to understand, but many datasets lack annotated explanation data, making it challenging to train models for explainable predictions. To address this, we investigate how to use existing…

Computation and Language · Computer Science 2025-02-10 Jing Yang , Max Glockner , Anderson Rocha , Iryna Gurevych

Mechanistic interpretability is an emerging diagnostic approach for neural models that has gained traction in broader natural language processing domains. This paradigm aims to provide attribution to components of neural systems where…

Information Retrieval · Computer Science 2025-01-20 Andrew Parry , Catherine Chen , Carsten Eickhoff , Sean MacAvaney

Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) has limited prior MI work in Machine Translation (MT) to word-level analyses. We study…

Computation and Language · Computer Science 2026-02-05 Théo Lasnier , Armel Zebaze , Djamé Seddah , Rachel Bawden , Benoît Sagot

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

Computation and Language · Computer Science 2022-05-24 Or Honovich , Uri Shaham , Samuel R. Bowman , Omer Levy

The impressive capabilities of deep learning models are often counterbalanced by their inherent opacity, commonly termed the "black box" problem, which impedes their widespread acceptance in high-trust domains. In response, the intersecting…

Machine Learning · Computer Science 2025-09-16 Mitali Raj

This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained…

Artificial Intelligence · Computer Science 2025-02-13 Tamar Rott Shaham , Sarah Schwettmann , Franklin Wang , Achyuta Rajaram , Evan Hernandez , Jacob Andreas , Antonio Torralba

Despite the growing body of work in interpretable machine learning, it remains unclear how to evaluate different explainability methods without resorting to qualitative assessment and user-studies. While interpretability is an inherently…

Machine Learning · Computer Science 2020-07-16 An-phi Nguyen , María Rodríguez Martínez

Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of…

Machine Learning · Statistics 2017-12-08 Fabian Offert

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Yao Qiang , Chengyin Li , Prashant Khanduri , Dongxiao Zhu

We present a mechanistic interpretability study of GPT-2 that causally examines how sentiment information is processed across its transformer layers. Using systematic activation patching across all 12 layers, we test the hypothesized…

Computation and Language · Computer Science 2025-12-09 Amartya Hatua

Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If…

Machine Learning · Computer Science 2026-01-07 Raphael Ronge , Markus Maier , Frederick Eberhardt