English
Related papers

Related papers: Improving Causal Interventions in Amnesic Probing …

200 papers

Estimating mutual information from text usually requires training a task-specific critic, which limits its use in low-data settings. We ask whether large language models can instead estimate pointwise mutual information zero-shot, using…

Computation and Language · Computer Science 2026-05-22 Juliette Woodrow , Chris Piech

Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little…

Machine Learning · Statistics 2018-06-26 Richard L. Phillips , Kyu Hyun Chang , Sorelle A. Friedler

Self-supervised objectives have driven major advances in NLP by leveraging large-scale unlabeled data, but such resources are scarce for many of the world's languages. Surprisingly, they have not been explored much for character-level…

Computation and Language · Computer Science 2025-06-06 Adam Wiemerslage , Katharina von der Wense

Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods…

Computation and Language · Computer Science 2023-05-18 Shadi Iskander , Kira Radinsky , Yonatan Belinkov

Recently, Provenance-based Intrusion Detection Systems (PIDSes) have been widely used for endpoint threat analysis. These studies can be broadly categorized into rule-based detection systems and learning-based detection systems. Among…

Cryptography and Security · Computer Science 2025-07-23 Wenrui Cheng , Tiantian Zhu , Shunan Jing , Jian-Ping Mei , Mingjun Ma , Jiaobo Jin , Zhengqiu Weng

Reinforcement Learning (RL) has become a key approach for enhancing the reasoning capabilities of large language models. However, prevalent RL approaches like proximal policy optimization and group relative policy optimization suffer from…

Machine Learning · Computer Science 2026-02-02 Jingtong Gao , Ling Pan , Yejing Wang , Rui Zhong , Chi Lu , Maolin Wang , Qingpeng Cai , Peng Jiang , Xiangyu Zhao

Language models can behave in unexpected and unsafe ways, and so it is valuable to monitor their outputs. Internal activations of language models encode additional information that could be useful for this. The baseline approach for…

Machine Learning · Computer Science 2025-04-30 Henk Tillman , Dan Mossing

Most modern NLP systems make use of pre-trained contextual representations that attain astonishingly high performance on a variety of tasks. Such high performance should not be possible unless some form of linguistic structure inheres in…

Computation and Language · Computer Science 2020-10-07 Lucas Torroba Hennigen , Adina Williams , Ryan Cotterell

Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Francesco Laiti , Davide Talon , Jacopo Staiano , Elisa Ricci

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

Computation and Language · Computer Science 2025-12-25 Shariqah Hossain , Lalana Kagal

User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs). This requires deleting or "forgetting" a set of data points from an already-trained model, which…

Machine Learning · Computer Science 2025-07-18 Vaidehi Patil , Elias Stengel-Eskin , Mohit Bansal

Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely…

Computation and Language · Computer Science 2025-01-23 Anmol Mekala , Vineeth Dorna , Shreya Dubey , Abhishek Lalwani , David Koleczek , Mukund Rungta , Sadid Hasan , Elita Lobo

This position paper investigates the potential of integrating insights from language impairment research and its clinical treatment to develop human-inspired learning strategies and evaluation frameworks for language models (LMs). We…

Computation and Language · Computer Science 2024-12-23 Dominique Brunato

Hallucination in large language models (LLMs) remains a critical barrier to their safe deployment. For hallucination detection to be practical in real-world scenarios, the use of efficient small models is essential to ensure low latency and…

Artificial Intelligence · Computer Science 2026-03-05 Zepeng Bao , Shen Zhou , Qiankun Pi , Jianhao Chen , Mayi Xu , Ming Zhong , Yuanyuan Zhu , Tieyun Qian

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Machine Learning · Computer Science 2022-12-01 Alain Andres , Esther Villar-Rodriguez , Javier Del Ser

Modern neural networks often encode unwanted concepts alongside task-relevant information, leading to fairness and interpretability concerns. Existing post-hoc approaches can remove undesired concepts but often degrade useful signals. We…

Machine Learning · Computer Science 2025-11-17 Floris Holstege , Shauli Ravfogel , Bram Wouters

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…

Machine Learning · Computer Science 2020-10-06 Mike Wu , Milan Mosse , Chengxu Zhuang , Daniel Yamins , Noah Goodman

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…

Computation and Language · Computer Science 2025-04-09 Pratiksha Thaker , Shengyuan Hu , Neil Kale , Yash Maurya , Zhiwei Steven Wu , Virginia Smith

Language Model (LM) pruning compresses the model by removing weights, nodes, or other parts of its architecture. Typically, pruning focuses on the resulting efficiency gains at the cost of effectiveness. However, when looking at how…

Computation and Language · Computer Science 2025-03-28 Pietro Tropeano , Maria Maistro , Tuukka Ruotsalo , Christina Lioma