While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy leakage, hallucinated outputs, and value misalignment, and can be maliciously used for generating toxic content and unethical purposes after been jailbroken. Therefore, in this survey, we present a comprehensive review of recent advancements aimed at mitigating these issues, organized across the four phases of LLM development and usage: data collecting and pre-training, fine-tuning and alignment, prompting and reasoning, and post-processing and auditing. We elaborate on the recent advances for enhancing the performance of LLMs in terms of privacy protection, hallucination reduction, value alignment, toxicity elimination, and jailbreak defenses. In contrast to previous surveys that focus on a single dimension of responsible LLMs, this survey presents a unified framework that encompasses these diverse dimensions, providing a comprehensive view of enhancing LLMs to better serve real-world applications.
Feature-Aware Malicious Output Detection and Mitigation
Tianjin University(天津大学);Meituan Group(美团集团);Tsinghua University(清华大学);Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);Monash University(莫纳什大学)
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University(航天信息安全部门、教育部、武汉大学计算机科学与工程学院);Ant Group(蚂蚁集团);Ant International(蚂蚁国际);School of Computing Technologies, Royal Melbourne Institute of Technology(皇家墨尔本理工学院计算机技术学院)
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Zhongguancun Laboratory(中关村实验室);Tsinghua University(清华大学);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Ant Group(蚂蚁集团)
"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
Institute of Computing Technology, CAS(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);UCLA(加州大学洛杉矶分校);University of California, Merced(加州大学默塞德分校);Tsinghua University(清华大学)
Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs
Indian Institute of Science Education and Research (IISER), Kolkata(印度科学教育与研究学院(加尔各答));Bosch India(博世印度公司);Manipal University Jaipur(斋浦尔马尼帕尔大学);University of Manchester(曼彻斯特大学);JTP Japan(JTP日本公司);A. P. Shah Institute of Technology(A. P. Shah理工学院)
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Griffith University(格里菲斯大学);Nanyang Technological University(南洋理工大学);University of New South Wales(新南威尔士大学);Zhejiang Key Laboratory of Digital Fashion and Data Governance, Zhejiang Sci-Tech University(浙江数字时尚与数据治理重点实验室,浙江科技大学)
Intelligent Detection and Mitigation of Carpet-Bombing DDoS Attacks in SDN Using Retrieval-Augmented Generation and Large Language Models
College of Electronics and Information Engineering, Shenzhen University(深圳大学电子与信息工程学院);ICNLab, Shenzhen Graduate School, Peking University(北京大学深圳研究生院ICN实验室)
Bias in Large Language Models: Origin, Evaluation, and Mitigation
Department of Statistics, George Washington University(乔治华盛顿大学统计学系);University of Connecticut(康奈尔大学);Saint Elizabeth University(圣艾利泽大学);The Pennsylvania State University(宾夕法尼亚州立大学)