English
Related papers

Related papers: Interpretability without actionability: mechanisti…

200 papers

Advancements in foundation models (FMs) have led to a paradigm shift in machine learning. The rich, expressive feature representations from these pre-trained, large-scale FMs are leveraged for multiple downstream tasks, usually via…

Machine Learning · Computer Science 2024-12-19 Jihye Choi , Jayaram Raghuram , Yixuan Li , Somesh Jha

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

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…

Machine Learning · Computer Science 2026-02-09 Navita Goyal , Hal Daumé

Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work, our goal is to propose a simple yet effective solution to…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Gabriela Csurka , Tyler L. Hayes , Diane Larlus , Riccardo Volpi

Concept Bottleneck Models (CBMs) provide inherent interpretability by first predicting a set of human-understandable concepts and then mapping them to labels through a simple classifier. While users can intervene in the concept space to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Hangzhou He , Lei Zhu , Kaiwen Li , Xinliang Zhang , Jiakui Hu , Ourui Fu , Zhengjian Yao , Yanye Lu

Multimodal LLMs (MLLMs) have reached remarkable levels of proficiency in understanding multimodal inputs. However, understanding and interpreting the behavior of such complex models is a challenging task, not to mention the dynamic shifts…

Artificial Intelligence · Computer Science 2025-08-14 Pegah Khayatan , Mustafa Shukor , Jayneel Parekh , Arnaud Dapogny , Matthieu Cord

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable - they should provide easy-to-interpret rationales for their behavior - so that passengers, insurance…

Computer Vision and Pattern Recognition · Computer Science 2017-04-03 Jinkyu Kim , John Canny

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of…

Machine Learning · Computer Science 2025-05-21 Woody Haosheng Gan , Deqing Fu , Julian Asilis , Ollie Liu , Dani Yogatama , Vatsal Sharan , Robin Jia , Willie Neiswanger

Concept bottleneck models (CBMs) are interpretable models that first predict a set of semantically meaningful features, i.e., concepts, from observations that are subsequently used to condition a downstream task. However, the model's…

Machine Learning · Computer Science 2023-12-04 Renos Zabounidis , Ini Oguntola , Konghao Zhao , Joseph Campbell , Simon Stepputtis , Katia Sycara

Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are…

Computation and Language · Computer Science 2025-07-10 Jord Nguyen , Khiem Hoang , Carlo Leonardo Attubato , Felix Hofstätter

While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users to perform interventional interactions on these concepts by…

Machine Learning · Computer Science 2024-06-05 David Steinmann , Wolfgang Stammer , Felix Friedrich , Kristian Kersting

Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like…

Artificial Intelligence · Computer Science 2025-08-12 Changqing Li , Tianlin Li , Xiaohan Zhang , Aishan Liu , Li Pan

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Computation and Language · Computer Science 2026-05-05 Or Shafran , Atticus Geiger , Mor Geva

Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by learning…

Machine Learning · Computer Science 2026-01-30 Antonio Almudévar , José Miguel Hernández-Lobato , Alfonso Ortega

Prior knowledge about the imaging physics provides a mechanistic forward operator that plays an important role in image reconstruction, although myriad sources of possible errors in the operator could negatively impact the reconstruction…

Image and Video Processing · Electrical Eng. & Systems 2022-11-04 Maryam Toloubidokhti , Nilesh Kumar , Zhiyuan Li , Prashnna K. Gyawali , Brian Zenger , Wilson W. Good , Rob S. MacLeod , Linwei Wang

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

Machine Learning · Computer Science 2025-11-04 Samaksh Bhargav , Zining Zhu

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Machine Learning · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is…

Computation and Language · Computer Science 2025-12-05 Xinyue Kang , Diwei Shi , Li Chen

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable,…

Machine Learning · Computer Science 2022-12-08 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas
‹ Prev 1 8 9 10 Next ›