This study introduces a taxonomy of stereotype content in contemporary large language models (LLMs). We prompt ChatGPT 3.5, Llama 3, and Mixtral 8x7B, three powerful and widely used LLMs, for the characteristics associated with 87 social categories (e.g., gender, race, occupations). We identify 14 stereotype dimensions (e.g., Morality, Ability, Health, Beliefs, Emotions), accounting for ~90% of LLM stereotype associations. Warmth and Competence facets were the most frequent content, but all other dimensions were significantly prevalent. Stereotypes were more positive in LLMs (vs. humans), but there was significant variability across categories and dimensions. Finally, the taxonomy predicted the LLMs' internal evaluations of social categories (e.g., how positively/negatively the categories were represented), supporting the relevance of a multidimensional taxonomy for characterizing LLM stereotypes. Our findings suggest that high-dimensional human stereotypes are reflected in LLMs and must be considered in AI auditing and debiasing to minimize unidentified harms from reliance in low-dimensional views of bias in LLMs.
Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?
Department of Electrical and Computer Engineering, Maroun Semaan Faculty of Engineering and Architecture（电气与计算机工程系，马鲁恩·塞马安工程与建筑学院）；American University of Beirut（贝鲁特美国大学）
Deconstructing Stereotypes: Scope-Conditioned Generation for Effective Multilingual Counterspeech
Université Côte d’Azur（蔚蓝海岸大学）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）；I3S（I3S实验室）；PRHLT Research Center, Universitat Politècnica de València（瓦伦西亚理工大学PRHLT研究中心）；ValgrAI Valencian Graduate School and Research Network of Artificial Intelligence（ValgrAI瓦伦西亚人工智能研究生院与研究网络）
Contextual StereoSet: Stress-Testing Bias Alignment Robustness in Large Language Models
Indian Institute of Information Technology, Allahabad (IIITA)（印度信息与技术研究所（Allahabad））；National Institute of Electronics and Information Technology (NIELIT)（国家电子与信息技术研究所）
How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University（吉林大学知识驱动人机智能工程研究中心）；International Center of Future Science, Jilin University（吉林大学未来科学国际中心）
Oraichain Labs（Oraichain实验室）；VinAI Research（VinAI研究院）；Florida International University（佛罗里达国际大学）；Hanoi University of Science and Technology（河内科技大学）；University of Oregon（俄勒冈大学）
Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection
College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）；AI Lab, China Mobile Communication Group Tianjin Co., Ltd.（中国移动通信集团天津有限公司人工智能实验室）
Graph-based Agent Memory: Taxonomy, Techniques, and Applications
The Hong Kong Polytechnic University（香港理工大学）；School of Information（信息学院）；Xiamen University（厦门大学）；School of Computing and Information Systems（计算与信息学院）；Singapore Management University（新加坡国立管理学院）；School of Artificial Intelligence（人工智能学院）
MIST: Towards Multi-dimensional Implicit BiaS Evaluation of LLMs for Theory of Mind
School of Software（软件学院）；Shandong University（山东大学）；National University of Singapore（新加坡国立大学）；School of Psychology（心理学学院）；Hainan Normal University（海南师范大学）
Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs
Warsaw University of Technology（华沙技术大学）；Wrocław University of Science and Technology（沃拉布大学科学技术学院）；University of Wrocław（沃拉布大学）；Lincoln University College, Petaling Jaya, Malaysian（林肯大学学院，吉隆坡，马来西亚）
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）
School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；Jisuan Institute of Technology, Beijing JudaoYouda Network Technology Co. Ltd.（智算技术研究所，北京judaoYouda网络技术有限公司）
Abusive music and song transformation using GenAI and LLMs
Transitional Artificial Intelligence Research Group, School of Mathematics and Statistics, UNSW Sydney, Australia（过渡人工智能研究组，数学与统计学学院）；Centre for Artificial Intelligence and Innovation, Pingla Institute, Sydney, Australia（人工智能与创新中心，Pingla研究所）
Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China（西安交通大学计算机科学与工程学院）；State Grid Henan Marketing Service Center, Henan, China（国网河南营销服务中心）；Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学网络安全学院）；School of Information Technology, Deakin University, Geelong, Australia（迪金大学信息技术学院）
