Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of temporal signal is typically overlooked, but is important if one aims to deploy a machine learning model over an extended period of time. In particular, language evolution causes data drift between time-steps in sequential decision-making tasks. Examples of such tasks include prediction of paper acceptance for yearly conferences (regular intervals) or author stance prediction for rumours on Twitter (irregular intervals). Inspired by successes in computer vision, we tackle data drift by sequentially aligning learned representations. We evaluate on three challenging tasks varying in terms of time-scales, linguistic units, and domains. These tasks show our method outperforming several strong baselines, including using all available data. We argue that, due to its low computational expense, sequential alignment is a practical solution to dealing with language evolution.
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Institute for Clarity in Documentation（文档清晰度研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康库尔中心）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕默研究实验室）
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
School of Life Sciences, IDG/McGovern Institute for Brain Research（生命科学学院，IDG/麦戈文脑科学研究所）；Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center（计算机科学与技术系，人工智能研究所，清华大学-博世联合机器学习中心，THBI实验室，BNRist中心）；Tsinghua University, Beijing, China（清华大学，北京，中国）
The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
Bosch Center for Artificial Intelligence (BCAI)（博世人工智能中心（BCAI））；Bosch (China) Investment Ltd.（博世（中国）投资有限公司）；School of Statistics, East China Normal University（东华大学统计学院）
Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
Research Institute of Criminal Psychiatry / Sex Offender Medical Center（犯罪精神病研究所以及性犯罪医疗中心）；Department of Neuropsychiatry, Kyoto University（京都大学神经精神病学系）
