中文
相关论文

相关论文: Adaptive Detoxification: Safeguarding General Capa…

200 篇论文

Large Language Models (LLMs) and Vision Language Models (VLMs) have recently shown promising capabilities in various scientific domain. In particular, these advances have opened new opportunities in drug discovery, where the ability to…

人工智能 · 计算机科学 2026-05-13 Jueon Park , Wonjune Jang , Jiwoo Lee , Yein Park , Jaewoo Kang

Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability…

计算与语言 · 计算机科学 2024-04-30 Ningyu Zhang , Bozhong Tian , Siyuan Cheng , Xiaozhuan Liang , Yi Hu , Kouying Xue , Yanjie Gou , Xi Chen , Huajun Chen

Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches…

计算与语言 · 计算机科学 2026-04-22 Wei Shao , Yihang Wang , Gaoyu Zhu , Ziqiang Cheng , Lei Yu , Jiafeng Guo , Xueqi Cheng

Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which seeks to accurately and efficiently modify a model's…

计算与语言 · 计算机科学 2025-12-05 Pengfei Cao , Zeao Ji , Daojian Zeng , Jun Zhao , Kang Liu

Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown…

计算与语言 · 计算机科学 2022-07-28 Farshid Faal , Ketra Schmitt , Jia Yuan Yu

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

计算与语言 · 计算机科学 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is the…

计算与语言 · 计算机科学 2025-04-23 Junfeng Fang , Houcheng Jiang , Kun Wang , Yunshan Ma , Shi Jie , Xiang Wang , Xiangnan He , Tat-seng Chua

Despite the ability to train capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. To this end, the past few years have witnessed a surge in techniques for editing LLMs, the objective of which…

计算与语言 · 计算机科学 2023-12-01 Yunzhi Yao , Peng Wang , Bozhong Tian , Siyuan Cheng , Zhoubo Li , Shumin Deng , Huajun Chen , Ningyu Zhang

Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models. We conduct this study on three dimensions: training…

计算与语言 · 计算机科学 2022-10-25 Boxin Wang , Wei Ping , Chaowei Xiao , Peng Xu , Mostofa Patwary , Mohammad Shoeybi , Bo Li , Anima Anandkumar , Bryan Catanzaro

Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amount of data which endows them with vast and diverse knowledge,…

计算与语言 · 计算机科学 2024-05-21 Tinh Son Luong , Thanh-Thien Le , Linh Ngo Van , Thien Huu Nguyen

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

计算与语言 · 计算机科学 2026-05-26 Shaz Furniturewala , Arkaitz Zubiaga

Knowledge editing technology is crucial for maintaining the accuracy and timeliness of large language models (LLMs) . However, the setting of this task overlooks a significant portion of commonsense knowledge based on free-text in the real…

计算与语言 · 计算机科学 2024-11-01 Xiusheng Huang , Yequan Wang , Jun Zhao , Kang Liu

Large language Model (LLM) unlearning, i.e., selectively removing information from LLMs, is vital for responsible model deployment. Differently, LLM knowledge editing aims to modify LLM knowledge instead of removing it. Though editing and…

机器学习 · 计算机科学 2025-05-27 Zexi Li , Xiangzhu Wang , William F. Shen , Meghdad Kurmanji , Xinchi Qiu , Dongqi Cai , Chao Wu , Nicholas D. Lane

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore the instance-level editing, while whether LLMs possess the capability to modify concepts…

计算与语言 · 计算机科学 2024-10-08 Xiaohan Wang , Shengyu Mao , Ningyu Zhang , Shumin Deng , Yunzhi Yao , Yue Shen , Lei Liang , Jinjie Gu , Huajun Chen

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

密码学与安全 · 计算机科学 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi

Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring…

计算与语言 · 计算机科学 2026-04-08 Jinhu Fu , Yan Bai , Longzhu He , Yihang Lou , Yanxiao Zhao , Li Sun , Sen Su

Knowledge editing and machine unlearning are two popular approaches for large language models (LLMs) to stay up-to-date. However, the knowledge updating mechanism of LLMs remains largely unexplored due to insufficient, isolated, and…

计算与语言 · 计算机科学 2026-03-26 Yinyi Luo , Zhexian Zhou , Hao Chen , Kai Qiu , Marios Savvides , Sharon Li , Jindong Wang

Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a…

计算与语言 · 计算机科学 2025-02-11 Paul Youssef , Zhixue Zhao , Christin Seifert , Jörg Schlötterer

Understanding and continuously refining multimodal molecular knowledge is crucial for advancing biomedicine, chemistry, and materials science. Molecule language models (MoLMs) have become powerful tools in these domains, integrating…

机器学习 · 计算机科学 2025-12-01 Zhenyu Lei , Patrick Soga , Yaochen Zhu , Yinhan He , Yushun Dong , Jundong Li

Large language models (LLMs) are deployed on mobile devices to power killer applications such as intelligent assistants. LLMs pre-trained on general corpora often hallucinate when handling personalized or unseen queries, leading to…

机器学习 · 计算机科学 2025-06-18 Zhenyan Lu , Daliang Xu , Dongqi Cai , Zexi Li , Wei Liu , Fangming Liu , Shangguang Wang , Mengwei Xu