English
Related papers

Related papers: Beyond Retention: Orchestrating Structural Safety …

200 papers

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Machine Learning · Computer Science 2026-05-29 Yan Chen , Taojie Zhu , Meng Zhang , Xin Chen , Jiaqi Huang , Dongyang Xu , Yizhi Wang

As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating text across various tasks. Nonetheless, the resilience of LLMs…

Computation and Language · Computer Science 2024-10-04 Bin Wang , Chengwei Wei , Zhengyuan Liu , Geyu Lin , Nancy F. Chen

Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evaluation methods, largely based on task performance or short-context behavior, provide…

Computation and Language · Computer Science 2026-05-26 Kumiko Tanaka-Ishii

This paper investigates the fundamental mechanisms driving plasticity loss in deep reinforcement learning (RL), a critical challenge where neural networks lose their ability to adapt to non-stationary environments. While existing research…

Machine Learning · Computer Science 2026-03-24 Zhiqiang He

Catastrophic forgetting is a pervasive issue for pre-trained language models (PLMs) during continual learning, where models lose previously acquired knowledge when sequentially trained on a series of tasks. The model's ability to retain old…

Computation and Language · Computer Science 2025-02-18 Biqing Zeng , Zehan Li , Aladdin Ayesh

Deep neural networks suffer from the catastrophic forgetting problem in the field of continual learning (CL). To address this challenge, we propose MGSER-SAM, a novel memory replay-based algorithm specifically engineered to enhance the…

Machine Learning · Computer Science 2024-05-16 Xingyu Li , Bo Tang

While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the basis, hindering knowledge compaction and exhausting capacity for future tasks. We observe…

Machine Learning · Computer Science 2026-05-28 Longhua Li , Lei Qi , Qi Tian , Xin Geng

Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue…

Computation and Language · Computer Science 2025-06-17 Qiyuan Deng , Xuefeng Bai , Kehai Chen , Yaowei Wang , Liqiang Nie , Min Zhang

Conceived in the early 1990s, Experience Replay (ER) has been shown to be a successful mechanism to allow online learning algorithms to reuse past experiences. Traditionally, ER can be applied to all machine learning paradigms (i.e.,…

Machine Learning · Computer Science 2016-10-19 Decebal Constantin Mocanu , Maria Torres Vega , Eric Eaton , Peter Stone , Antonio Liotta

Various methods using machine and deep learning have been proposed to tackle different tasks in predictive process monitoring, forecasting for an ongoing case e.g. the most likely next event or suffix, its remaining time, or an…

Machine Learning · Computer Science 2022-12-14 Jari Peeperkorn , Seppe vanden Broucke , Jochen De Weerdt

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model…

Machine Learning · Computer Science 2018-12-21 Matthew Riemer , Tim Klinger , Djallel Bouneffouf , Michele Franceschini

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Software Engineering · Computer Science 2025-01-09 Benjamin Steenhoek , Md Mahbubur Rahman , Monoshi Kumar Roy , Mirza Sanjida Alam , Hengbo Tong , Swarna Das , Earl T. Barr , Wei Le

Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal difference (TD) error empirically enhancing the performance.…

Machine Learning · Computer Science 2024-09-20 Changling Li , Zhang-Wei Hong , Pulkit Agrawal , Divyansh Garg , Joni Pajarinen

Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training. Knowledge editing techniques address this issue without the need for…

Computation and Language · Computer Science 2024-10-16 Yuchen Cai , Ding Cao

Reinforcement learning (RL) has demonstrated the ability to maintain the plasticity of the policy throughout short-term training in aerial robot control. However, these policies have been shown to loss of plasticity when extended to…

Robotics · Computer Science 2025-03-11 Ali Tahir Karasahin , Ziniu Wu , Basaran Bahadir Kocer

Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…

Computation and Language · Computer Science 2025-02-13 Çağatay Yıldız , Nishaanth Kanna Ravichandran , Nitin Sharma , Matthias Bethge , Beyza Ermis

The memory of contemporary Large Language Models is bound by a physical paradox: as they learn, they fill up. The linear accumulation (O(N)) of Key-Value states treats context as a warehouse of static artifacts, eventually forcing a…

Neural and Evolutionary Computing · Computer Science 2025-12-24 Tarik Houichime , Abdelghani Souhar , Younes El Amrani

Online Continual learning is a challenging learning scenario where the model must learn from a non-stationary stream of data where each sample is seen only once. The main challenge is to incrementally learn while avoiding catastrophic…

Machine Learning · Computer Science 2022-06-24 Mattia Sangermano , Antonio Carta , Andrea Cossu , Davide Bacciu

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…

Machine Learning · Computer Science 2024-07-17 Luke Yang , Levin Kuhlmann , Gideon Kowadlo

Reinforcement learning (RL) has shown impressive success in exploring high-dimensional environments to learn complex tasks, but can often exhibit unsafe behaviors and require extensive environment interaction when exploration is…

Machine Learning · Computer Science 2021-09-22 Albert Wilcox , Ashwin Balakrishna , Brijen Thananjeyan , Joseph E. Gonzalez , Ken Goldberg