English
Related papers

Related papers: Circuit Component Reuse Across Tasks in Transforme…

200 papers

Large language models (LLMs) exhibit remarkable in-context learning (ICL) capabilities. However, the underlying working mechanism of ICL remains poorly understood. Recent research presents two conflicting views on ICL: One emphasizes the…

Computation and Language · Computer Science 2024-10-10 Anhao Zhao , Fanghua Ye , Jinlan Fu , Xiaoyu Shen

The paper explores how video models trained for classification tasks represent nuanced, hidden semantic information that may not affect the final outcome, a key challenge for Trustworthy AI models. Through Explainable and Interpretable AI…

Machine Learning · Computer Science 2026-03-13 Sai V R Chereddy

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted…

Machine Learning · Computer Science 2024-02-20 Zhengfu He , Xuyang Ge , Qiong Tang , Tianxiang Sun , Qinyuan Cheng , Xipeng Qiu

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

Machine Learning · Computer Science 2024-09-27 Tong Yang , Yu Huang , Yingbin Liang , Yuejie Chi

Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directions that steer prompted behavior. However, it remains…

Machine Learning · Computer Science 2026-05-20 Wei Tang , Xinyan Jiang , Fakhri Karray , Lijie Hu

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery…

Machine Learning · Computer Science 2025-02-10 Tal Haklay , Hadas Orgad , David Bau , Aaron Mueller , Yonatan Belinkov

Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Jing Zhao , Shengjian Wu , Li Sun , Qingli Li

As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting human-understandable algorithms to explain their behavior.…

Machine Learning · Computer Science 2025-03-03 Maxime Méloux , Silviu Maniu , François Portet , Maxime Peyrard

Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences…

Information Retrieval · Computer Science 2025-07-22 Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the…

Machine Learning · Computer Science 2022-07-26 John Sipple , Abdou Youssef

Neural network models have achieved high performance on a wide variety of complex tasks, but the algorithms that they implement are notoriously difficult to interpret. It is often necessary to hypothesize intermediate variables involved in…

Computation and Language · Computer Science 2025-02-13 Michael A. Lepori , Thomas Serre , Ellie Pavlick

Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recovering these circuits typically requires a bespoke analytical pipeline for each new task.…

Machine Learning · Computer Science 2026-05-27 Barsat Khadka

We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis).…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Han Xue , Qianru Sun , Li Song , Wenjun Zhang , Zhiwu Huang

Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these crucial subnetworks remains opaque. To gain an understanding…

Computation and Language · Computer Science 2025-07-17 Huaizhi Ge , Frank Rudzicz , Zining Zhu

Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper further investigates the `texture bias' in CNNs. To this end,…

Computer Vision and Pattern Recognition · Computer Science 2021-10-22 Amin Banitalebi-Dehkordi , Yong Zhang

Generalization to novel compound tasks under distribution shift is important for deploying transformer-based language models (LMs). This work investigates Chain-of-Thought (CoT) reasoning as a means to enhance OOD generalization. Through…

Computation and Language · Computer Science 2026-03-31 Ru Wang , Wei Huang , Selena Song , Haoyu Zhang , Qian Niu , Yusuke Iwasawa , Yutaka Matsuo , Jiaxian Guo

Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power. However, our understanding of the inner workings and conditions of apparition of CoT capabilities…

Machine Learning · Computer Science 2024-10-29 Vivien Cabannes , Charles Arnal , Wassim Bouaziz , Alice Yang , Francois Charton , Julia Kempe

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…

Machine Learning · Computer Science 2023-11-09 Jinyung Hong , Keun Hee Park , Theodore P. Pavlic

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Machine Learning · Computer Science 2025-11-26 Wei Chen , Jingxi Yu , Zichen Miao , Qiang Qiu

In-context learning (ICL) has emerged as a powerful paradigm for easily adapting Large Language Models (LLMs) to various tasks. However, our understanding of how ICL works remains limited. We explore a simple model of ICL in a controlled…

Machine Learning · Computer Science 2025-09-03 Omar Naim , Guilhem Fouilhé , Nicholas Asher