English
Related papers

Related papers: Understanding Empirical Unlearning with Combinator…

200 papers

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Computation and Language · Computer Science 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of…

Machine Learning · Computer Science 2024-05-28 Ouail Kitouni , Niklas Nolte , Víctor Samuel Pérez-Díaz , Sokratis Trifinopoulos , Mike Williams

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez

Unsupervised learning allows us to leverage unlabelled data, which has become abundantly available, and to create embeddings that are usable on a variety of downstream tasks. However, the typical lack of interpretability of unsupervised…

Machine Learning · Computer Science 2023-09-29 Gregory Scafarto , Madalina Ciortan , Simon Tihon , Quentin Ferre

Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate…

Computation and Language · Computer Science 2024-10-16 Deniz Bayazit , Negar Foroutan , Zeming Chen , Gail Weiss , Antoine Bosselut

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

There exist applications of reinforcement learning like medicine where policies need to be ''interpretable'' by humans. User studies have shown that some policy classes might be more interpretable than others. However, it is costly to…

Machine Learning · Computer Science 2025-03-12 Hector Kohler , Quentin Delfosse , Waris Radji , Riad Akrour , Philippe Preux

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

Machine Learning · Computer Science 2025-05-28 Geyu Liang , Senne Michielssen , Salar Fattahi

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such…

Artificial Intelligence · Computer Science 2024-04-04 Julien Ferry , Ulrich Aïvodji , Sébastien Gambs , Marie-José Huguet , Mohamed Siala

Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge, and copyrighted content. We introduce the problem of Large…

Computation and Language · Computer Science 2025-02-18 Yu Wang , Ruihan Wu , Zexue He , Xiusi Chen , Julian McAuley

Various studies have attempted to remove sensitive or private knowledge from a language model to prevent its unauthorized exposure. However, prior studies have overlooked the complex and interconnected nature of knowledge, where related…

Computation and Language · Computer Science 2025-10-28 Nakyeong Yang , Minsung Kim , Seunghyun Yoon , Joongbo Shin , Kyomin Jung

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

Machine Learning · Computer Science 2023-07-17 Mara Graziani , Laura O' Mahony , An-Phi Nguyen , Henning Müller , Vincent Andrearczyk

Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet…

Machine Learning · Computer Science 2017-03-07 Zachary C. Lipton

Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a…

Computers and Society · Computer Science 2026-05-08 Isabelle Lee , Emmy Liu , Cathy Jiao , Brihi Joshi , Dani Yogatama , Fazl Barez , Michael Saxon

Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore,…

Machine Learning · Computer Science 2024-12-03 Martin Atzmueller , Tim Bohne , Patricia Windler

Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to…

Machine Learning · Computer Science 2024-03-13 Vinay Chakravarthi Gogineni , Esmaeil S. Nadimi

Incorporation of a new knowledge into neural networks with simultaneous preservation of the previous one is known to be a nontrivial problem. This problem becomes even more complex when new knowledge is contained not in new training…

Machine Learning · Computer Science 2019-09-10 Mikhail Iu. Leontev , Viktoriia Islenteva , Sergey V. Sukhov

In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but also related implicit knowledge. To this end, we begin by…

Computation and Language · Computer Science 2025-10-10 Huazheng Wang , Yongcheng Jing , Haifeng Sun , Yingjie Wang , Jingyu Wang , Jianxin Liao , Dacheng Tao

The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…

Machine Learning · Computer Science 2023-11-14 Tsun-Hsuan Wang , Wei Xiao , Tim Seyde , Ramin Hasani , Daniela Rus