English
Related papers

Related papers: Counterfactual Memorization in Neural Language Mod…

200 papers

People can acquire knowledge in an unsupervised manner by reading, and compose the knowledge to make novel combinations. In this paper, we investigate whether pretrained language models can perform compositional generalization in a…

Computation and Language · Computer Science 2022-10-21 Xiao Liu , Yansong Feng , Jizhi Tang , Chengang Hu , Dongyan Zhao

Open-domain dialogue generation suffers from the data insufficiency problem due to the vast size of potential responses. In this paper, we propose to explore potential responses by counterfactual reasoning. Given an observed response, the…

Machine Learning · Computer Science 2020-10-12 Qingfu Zhu , Weinan Zhang , Ting Liu , William Yang Wang

Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of…

Machine Learning · Computer Science 2025-03-18 Shengyuan Hu , Yiwei Fu , Zhiwei Steven Wu , Virginia Smith

Over-parameterized deep neural networks are able to achieve excellent training accuracy while maintaining a small generalization error. It has also been found that they are able to fit arbitrary labels, and this behaviour is referred to as…

Machine Learning · Computer Science 2021-12-17 Futong Liu , Tao Lin , Martin Jaggi

Despite the advanced capabilities of large language models (LLMs), their temporal reasoning ability remains underdeveloped. Prior works have highlighted this limitation, particularly in maintaining temporal consistency when understanding…

Computation and Language · Computer Science 2025-06-18 Jongho Kim , Seung-won Hwang

Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks $\textit{memorize}$ "hard" examples in the final few layers of the model. Memorization refers…

Machine Learning · Computer Science 2023-07-20 Pratyush Maini , Michael C. Mozer , Hanie Sedghi , Zachary C. Lipton , J. Zico Kolter , Chiyuan Zhang

Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. Much prior work has studied such verbatim memorization using observational data. To complement such work, we…

Computation and Language · Computer Science 2024-07-26 Jing Huang , Diyi Yang , Christopher Potts

An exhaustive study on neural network language modeling (NNLM) is performed in this paper. Different architectures of basic neural network language models are described and examined. A number of different improvements over basic neural…

Computation and Language · Computer Science 2017-08-25 Dengliang Shi

Large language models (LLMs) suffer from forgetting of upstream knowledge when fine-tuned. Despite efforts on mitigating forgetting, few have investigated how forgotten upstream examples are dependent on newly learned tasks. Insights on…

Machine Learning · Computer Science 2025-12-09 Xisen Jin , Xiang Ren

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual…

Computation and Language · Computer Science 2022-10-21 Shaobo Li , Xiaoguang Li , Lifeng Shang , Chengjie Sun , Bingquan Liu , Zhenzhou Ji , Xin Jiang , Qun Liu

Supervised learning in Neural Machine Translation (NMT) typically follows a teacher forcing paradigm where reference tokens constitute the conditioning context in the model's prediction, instead of its own previous predictions. In order to…

Computation and Language · Computer Science 2023-07-18 Nathaniel Berger , Miriam Exel , Matthias Huck , Stefan Riezler

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to…

Machine Learning · Computer Science 2019-08-19 Yue Wang , Yao Wan , Chenwei Zhang , Lixin Cui , Lu Bai , Philip S. Yu

Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models. In particular, it is vital to minimize a model's memorization…

Computation and Language · Computer Science 2023-06-02 Stella Biderman , USVSN Sai Prashanth , Lintang Sutawika , Hailey Schoelkopf , Quentin Anthony , Shivanshu Purohit , Edward Raff

As machine learning (ML) models become more widely deployed in high-stakes applications, counterfactual explanations have emerged as key tools for providing actionable model explanations in practice. Despite the growing popularity of…

Machine Learning · Computer Science 2022-12-16 Martin Pawelczyk , Chirag Agarwal , Shalmali Joshi , Sohini Upadhyay , Himabindu Lakkaraju

Overfitting is a well-known issue in machine learning that occurs when a model struggles to generalize its predictions to new, unseen data beyond the scope of its training set. Traditional techniques to mitigate overfitting include early…

Machine Learning · Computer Science 2025-12-09 Flavio Giorgi , Fabiano Veglianti , Fabrizio Silvestri , Gabriele Tolomei

State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation…

Computation and Language · Computer Science 2022-03-16 Michael Tänzer , Sebastian Ruder , Marek Rei

We present a reproduction study of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals" (Ortu et al., 2024), which investigates competition of mechanisms in language models between factual recall and…

Computation and Language · Computer Science 2025-07-01 Asen Dotsinski , Udit Thakur , Marko Ivanov , Mohammad Hafeez Khan , Maria Heuss

Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require large amounts of annotated data. These resources are often based on language data available in…

Computation and Language · Computer Science 2020-11-10 Farhad Nooralahzadeh

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…

Computation and Language · Computer Science 2026-05-28 Yuefeng Peng , Parnian Afshar , Megan Ganji , Thomas Butler , Amir Houmansadr , Mingxian Wang , Dezhi Hong

Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data. In order to cleanly measure and…

Computation and Language · Computer Science 2024-07-30 Till Speicher , Mohammad Aflah Khan , Qinyuan Wu , Vedant Nanda , Soumi Das , Bishwamittra Ghosh , Krishna P. Gummadi , Evimaria Terzi
‹ Prev 1 4 5 6 7 8 10 Next ›