English
Related papers

Related papers: Modifying Memories in Transformer Models

200 papers

Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of…

Computation and Language · Computer Science 2024-03-12 Xiaopeng Li , Shasha Li , Shezheng Song , Jing Yang , Jun Ma , Jie Yu

Memory is one of the most essential cognitive functions serving as a repository of world knowledge and episodes of activities. In recent years, large-scale pre-trained language models have shown remarkable memorizing ability. On the…

Computation and Language · Computer Science 2024-03-14 Boxi Cao , Qiaoyu Tang , Hongyu Lin , Shanshan Jiang , Bin Dong , Xianpei Han , Jiawei Chen , Tianshu Wang , Le Sun

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

Identifying critical research within the growing body of academic work is an intrinsic aspect of conducting quality research. Systematic review processes used in evidence-based medicine formalise this as a procedure that must be followed in…

Digital Libraries · Computer Science 2024-10-14 John Hawkins , David Tivey

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…

Computation and Language · Computer Science 2019-06-03 Alexandra Chronopoulou , Christos Baziotis , Alexandros Potamianos

While transformers demonstrate impressive performance on many knowledge intensive (KI) tasks, their ability to serve as implicit knowledge bases (KBs) remains limited, as shown on several slot-filling, question-answering (QA), fact…

Computation and Language · Computer Science 2022-03-21 Nic Jedema , Thuy Vu , Manish Gupta , Alessandro Moschitti

The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…

Computation and Language · Computer Science 2024-03-06 Bo Wang , Tianxiang Sun , Hang Yan , Siyin Wang , Qingyuan Cheng , Xipeng Qiu

Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, several machine unlearning algorithms have been proposed to…

Computation and Language · Computer Science 2025-05-27 Keivan Rezaei , Khyathi Chandu , Soheil Feizi , Yejin Choi , Faeze Brahman , Abhilasha Ravichander

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

In parallel to their overwhelming success across NLP tasks, language ability of deep Transformer networks, pretrained via language modeling (LM) objectives has undergone extensive scrutiny. While probing revealed that these models encode a…

Computation and Language · Computer Science 2021-10-19 Olga Majewska , Ivan Vulić , Goran Glavaš , Edoardo M. Ponti , Anna Korhonen

Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models with constrained parameter sizes. However, from a…

Computation and Language · Computer Science 2025-11-24 Yihuai Hong , Yiran Zhao , Wei Tang , Yang Deng , Yu Rong , Wenxuan Zhang

Large-scale training datasets lie at the core of the recent success of neural machine translation (NMT) models. However, the complex patterns and potential noises in the large-scale data make training NMT models difficult. In this work, we…

Computation and Language · Computer Science 2020-10-07 Wenxiang Jiao , Xing Wang , Shilin He , Irwin King , Michael R. Lyu , Zhaopeng Tu

Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…

Computation and Language · Computer Science 2025-06-23 Daniel Christoph , Max Ploner , Patrick Haller , Alan Akbik

Soft prompts have been recently proposed as a tool for adapting large frozen language models (LMs) to new tasks. In this work, we repurpose soft prompts to the task of injecting world knowledge into LMs. We introduce a method to train soft…

Computation and Language · Computer Science 2022-10-11 Cicero Nogueira dos Santos , Zhe Dong , Daniel Cer , John Nham , Siamak Shakeri , Jianmo Ni , Yun-hsuan Sung

Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training…

Machine Learning · Computer Science 2024-01-12 Pratyush Maini , Zhili Feng , Avi Schwarzschild , Zachary C. Lipton , J. Zico Kolter

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce…

Computation and Language · Computer Science 2024-10-11 Kerem Zaman , Leshem Choshen , Shashank Srivastava

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…

Machine Learning · Statistics 2023-11-08 Alberto Bietti , Vivien Cabannes , Diane Bouchacourt , Herve Jegou , Leon Bottou

While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall via unseen queries remain poorly understood. Common two-stage training strategies, which…

Computation and Language · Computer Science 2026-05-29 Ying Zhang , Benjamin Heinzerling , Dongyuan Li , Kentaro Inui

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…