English
Related papers

Related papers: Forgetting Exceptions is Harmful in Language Learn…

200 papers

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…

Computation and Language · Computer Science 2022-11-07 Shuhao Gu , Bojie Hu , Yang Feng

Artificial neural networks can generalize productively to novel contexts. Can they also learn exceptions to those productive rules? We explore this question using the case of restrictions on English passivization (e.g., the fact that "The…

Computation and Language · Computer Science 2023-06-12 Cara Su-Yi Leong , Tal Linzen

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Computation and Language · Computer Science 2025-10-20 Jessy Lin , Luke Zettlemoyer , Gargi Ghosh , Wen-Tau Yih , Aram Markosyan , Vincent-Pierre Berges , Barlas Oğuz

Large language models exhibit a remarkable capacity for in-context learning, where they learn to solve tasks given a few examples. Recent work has shown that transformers can be trained to perform simple regression tasks in-context. This…

Machine Learning · Computer Science 2026-04-03 Hrayr Harutyunyan , Rafayel Darbinyan , Samvel Karapetyan , Hrant Khachatrian

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential…

Computation and Language · Computer Science 2024-12-30 Megan Ung , Alicia Sun , Samuel J. Bell , Bhaktipriya Radharapu , Levent Sagun , Adina Williams

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Machine Learning · Computer Science 2024-01-17 Sungmin Cha , Sungjun Cho , Dasol Hwang , Honglak Lee , Taesup Moon , Moontae Lee

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are…

Computation and Language · Computer Science 2024-08-12 Verna Dankers , Ivan Titov

Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is not memorization itself, but its target: vanilla SFT drives…

Machine Learning · Computer Science 2026-05-26 Ruiying Peng , Mengyu Yang , Jing Lei , Xiaohui Li , Xueyu Wu , Xinlei Chen

Concerned with privacy threats, memorization in LLMs is often seen as undesirable, specifically for learning. In this paper, we study whether memorization can be avoided when optimally learning a language, and whether the privacy threat…

Machine Learning · Computer Science 2025-07-22 Bishwamittra Ghosh , Soumi Das , Qinyuan Wu , Mohammad Aflah Khan , Krishna P. Gummadi , Evimaria Terzi , Deepak Garg

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexical content, but…

Computation and Language · Computer Science 2021-06-02 Lang Yu , Allyson Ettinger

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

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain…

Computation and Language · Computer Science 2024-07-23 Tongyao Zhu , Qian Liu , Liang Pang , Zhengbao Jiang , Min-Yen Kan , Min Lin

Understanding memorisation in language models has practical and societal implications, e.g., studying models' training dynamics or preventing copyright infringements. Prior work defines memorisation as the causal effect of training with an…

Machine Learning · Computer Science 2024-10-17 Pietro Lesci , Clara Meister , Thomas Hofmann , Andreas Vlachos , Tiago Pimentel

People exhibit a tendency to generalize a novel noun to the basic-level in a hierarchical taxonomy -- a cognitively salient category such as "dog" -- with the degree of generalization depending on the number and type of exemplars. Recently,…

Computation and Language · Computer Science 2016-02-19 Erin Grant , Aida Nematzadeh , Suzanne Stevenson

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Computation and Language · Computer Science 2023-02-10 Joel Jang , Seungone Kim , Seonghyeon Ye , Doyoung Kim , Lajanugen Logeswaran , Moontae Lee , Kyungjae Lee , Minjoon Seo

In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic…

Machine Learning · Computer Science 2021-04-06 Timothée Lesort , Andrei Stoian , David Filliat

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

Machine Learning · Computer Science 2025-01-24 Junhao Zheng , Xidi Cai , Shengjie Qiu , Qianli Ma

Despite the remarkable capabilities of modern large language models (LLMs), the mechanisms behind their problem-solving abilities remain elusive. In this work, we aim to better understand how the learning dynamics of LLM finetuning shapes…

Machine Learning · Computer Science 2024-11-19 Katie Kang , Amrith Setlur , Dibya Ghosh , Jacob Steinhardt , Claire Tomlin , Sergey Levine , Aviral Kumar

Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote. However, a single average performance score on the entire test set is inadequate in determining such…

Computation and Language · Computer Science 2023-11-17 Prafulla Kumar Choubey , Alexander R. Fabbri , Caiming Xiong , Chien-Sheng Wu