As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, such as non-toxicity and logical consistency, as well as task- and situation-specific constraints. Controlling the output through instructions is a simple and tempting approach; however, it remains brittle, is opaque in how it influences model behavior, and thus cannot reliably ensure constraint satisfaction. Moreover, most recent controlled text generation (CTG) methods require access to the internal components of language models--such as weights or logits--making them incompatible with popular API-based LLMs. In this work, we propose LaSEr-Edit, a constraint-satisfying text revision method that can be applied to any LLMs, black- or white-box. We first find that lightweight, task-specific energy-based models (EBMs) achieve error-localization performance competitive with or even better than that of much larger LLMs, while operating substantially faster. Based on this finding, we propose two variants of text revision methods that incorporate energy-based error localization: LaSEr-LLM Edit, which instructs an LLM to edit text given EBM-predicted error spans, and LaSEr-EBM Edit, which uses the EBM not only for localization but also for editing by reranking edit candidates. Through experiments in diverse single-constraint control tasks, we show that LaSEr-LLM Edit controls text better than plain LLM-based editing in most of the tasks. We also find that LaSEr-EBM Edit further improves the control performance of LaSEr-LLM Edit and achieves among the strongest controllability across all tasks. Furthermore, we find that LaSEr-Edit, especially LaSEr-EBM Edit, performs well even when multiple constraints are controlled simultaneously.
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS（智能信息处理重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Agriculture Information Institute, CAAS（农业信息研究所，中国农业科学院）
Constraining Sequential Model Editing with Editing Anchor Compression
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China（中国科学技术大学语音及语言信息处理国家工程研究中心）；Zhejiang University（浙江大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
National Engineering Research Center of Speech and Language Information Processing（语音与语言信息处理国家级工程研究中心）；University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research（iFLYTEK研究院）；University of California, Los Angeles（美国加州大学洛杉矶分校）
Uncovering Overfitting in Large Language Model Editing
Shandong University（山东大学）；School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）；New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Knowledge Graph Enhanced Large Language Model Editing
School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs
School of Computer Science and Technology, Tianjin University（天津大学计算机科学与技术学院）；Kexin Technology（可心科技）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Hunyuan（腾讯混元）；College of Computer Science, Chongqing University（重庆大学计算机学院）
Potential and Challenges of Model Editing for Social Debiasing
Zhejiang University School of Engineering（浙江大学工程学院）；Westlake University（西湖大学）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究所）
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
Shanghai AI Laboratory（上海人工智能实验室）；Nanyang Technological University（南洋理工大学）；Monash University（莫纳什大学）；SenseTime Research（商汤科技研究院）；Hong Kong University of Science and Technology（香港科技大学）
EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University（人工智能研究所、先进系统研究室、智能网络中心、信息科学研究中心和人工智能计划，首尔国立大学）
DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
School of Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程学院）；Kunming University of Science and Technology（昆明理工大学）；NiuTrans Research, Shenyang, China（新译研究）
