Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(人工智能通用基础理论国家重点实验室,智能科学与技术学院,北京大学);Yuanpei College, Peking University(元培学院,北京大学);School of Psychological and Cognitive Sciences, Peking University(心理学与认知科学学院,北京大学);Key Laboratory of Machine Perception (Ministry of Education), Peking University(机器感知重点实验室(教育部),北京大学);PKU-Wuhan Institute for Artificial Intelligence(北京大学-武汉人工智能研究院)
Haoran Ye, Tianze Zhang, Yuhang Xie, Liyuan Zhang, Yuanyi Ren, Xin Zhang, Guojie Song
Values are core drivers of individual and collective perception, cognition, and behavior. Value systems, such as Schwartz's Theory of Basic Human Values, delineate the hierarchy and interplay among these values, enabling cross-disciplinary investigations into decision-making and societal dynamics. Recently, the rise of Large Language Models (LLMs) has raised concerns regarding their elusive intrinsic values. Despite growing efforts in evaluating, understanding, and aligning LLM values, a psychologically grounded LLM value system remains underexplored. This study addresses the gap by introducing the Generative Psycho-Lexical Approach (GPLA), a scalable, adaptable, and theoretically informed method for constructing value systems. Leveraging GPLA, we propose a psychologically grounded five-factor value system tailored for LLMs. For systematic validation, we present three benchmarking tasks that integrate psychological principles with cutting-edge AI priorities. Our results reveal that the proposed value system meets standard psychological criteria, better captures LLM values, improves LLM safety prediction, and enhances LLM alignment, when compared to the canonical Schwartz's values.
Human Psychometric Questionnaires Mischaracterize LLM Behavior
Graduate School of Data Science, Seoul National University(首尔国立大学数据科学研究生院);Department of Communication, Interdisciplinary Program in Artificial Intelligence, Seoul National University(首尔国立大学通信系人工智能交叉学科项目)
NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages
HKUST(香港科技大学);IndoNLP(印尼自然语言处理研究所);MBZUAI(穆罕默德·本·扎耶德人工智能大学);Bina Nusantara University(建国大学);Bloomberg(彭博社);Institut Teknologi Bandung(万隆理工学院);Kanda University of International Studies(神田外语大学)
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
Institute for Artificial Intelligence(人工智能研究院);School of Psychological and Cognitive Sciences(心理学与认知科学学院);School of Intelligence Science and Technology(智能科学与技术学院);State Key Laboratory of General AI(通用人工智能国家重点实验室);Beijing Key Laboratory of Behavior and Mental Health(北京行为与心理健康重点实验室);PKU-Changsha Institute for Computing and Digital Economy(北京大学长沙计算与数字经济研究院)
Psychosis involves a deficit of information compression in connected speech
Universitat Pompeu Fabra(庞培法布拉大学);Dokuz Eylul University(多库兹·埃吕尔大学);McLean Hospital(麦克莱恩医院);Harvard Medical School(哈佛医学院);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院);Institut Català de Recerca i Estudis Avançats (ICREA)(加泰罗尼亚研究与高级研究院(ICREA))
LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data
Melbourne School of Psychological Sciences, The University of Melbourne(墨尔本大学心理学科学学院);School of Computing and Information Systems, The University of Melbourne(墨尔本大学计算与信息学院);School of Electronic Engineering and Computer Science, Queen Mary University of London(伦敦女王学院电子工程与计算机科学学院);The Alan Turing Institute, London(伦敦艾伦·图灵研究所);Language Technology Lab, University of Cambridge(剑桥大学语言技术实验室)
Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
Centre for Language Studies, Centre for Language and Speech Technology, Radboud University,Nijmegen, The Netherlands(语言研究所以及语言与语音技术中心,拉德堡德大学,尼姆egen,荷兰);Behavioural Science Institute, Radboud University, Nijmegen, The Netherlands(行为科学研究所,拉德堡德大学,尼姆egen,荷兰)
Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
Apart Research;Odyssean Institute;London School of Economics and Political Science(伦敦政治经济学院);Stanford Institute for Human-Centered AI(斯坦福大学以人为本人工智能研究所)
Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings
Universidad Politécnica de Madrid(马德里理工大学);Politecnico di Milano(米兰理工大学);Massachusetts Institute of Technology(麻省理工学院);University of California(加利福尼亚大学);University of Hong Kong(香港大学);Ghent University(根特大学)
Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory
Hanyang University(翰阳大学);Miami University(迈阿密大学);The Catholic University of Korea College of Medicine(韩国天主教大学医学院);Artificial Consciousness Lab, MODULABS(意识实验室,MODULABS)
ALIGN: Word Association Learning for Cultural Alignment in Large Language Models
School of Computing and Information Systems, The University of Melbourne(计算与信息系统学院,墨尔本大学);Melbourne Data Analytics Platform, The University of Melbourne(墨尔本数据分析平台,墨尔本大学);Faculty of Information Technology, Monash University(信息技术学院,墨尔本大学)
"Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior
Brain & Creativity Institute, University of Southern California(大脑与创造力研究所,南加州大学);Department of Psychology, University of Southern California(心理学系,南加州大学);Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart(智能系统反思交流论坛,斯图加特大学)
Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts
Information Sciences Institute, University of Southern California(南加州大学信息科学学院);Iovine and Young Academy, University of Southern California(南加州大学约万与杨学院);In Vivo Group
Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead
Max Planck Institute for Intelligent Systems, Tübingen(马克斯·普朗克智能系统研究所,图宾根);ETH Zurich, Zurich(苏黎世联邦理工学院,苏黎世);University of Tübingen, Methods Center, Tübingen(图宾根大学,方法中心,图宾根);Massachusetts Institute of Technology, Cambridge(麻省理工学院,剑桥)
InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models
Department of Mathematics, IIT Delhi(印度德里理工学院数学系);Department of Electrical Engineering, IIT Delhi(印度德里理工学院电气工程系);Department of Computer Science and Engineering, IIIT Manipur(曼尼普尔理工学院计算机科学与工程系)
Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness
Department of Experimental Psychology, University of Oxford(心理学实验系,牛津大学);Uehiro Oxford Institute, University of Oxford(牛津大学欧胡罗研究所);Psychology Programme, School of Social Sciences, Nanyang Technological University(南洋理工大学社会科学学院心理学项目);Department of Communication and Culture, BI Norwegian Business School(BI挪威商学院传播与文化系)
A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification
Bioinformatics Multidisciplinary Environment (BioME)(生物信息学多学科环境(BioME));Digital Metropolis Institute (IMD)(数字大都市研究所(IMD));Federal University of Rio Grande do Norte (UFRN)(北里奥格兰德联邦大学(UFRN));Mobile Brain(移动大脑(公司));Institute of Psychiatry (IPUB)(精神病学研究所(IPUB));Federal University of Rio de Janeiro (UFRJ)(里约热内卢联邦大学(UFRJ));The University of Exeter(埃克塞特大学);Institute for Data Science and Artificial Intelligence at the University of Exeter(埃克塞特大学数据科学与人工智能研究所);The University of Sheffield(谢菲尔德大学);Pontifical Catholic University of Rio Grande do Sul (PUCRS)(南里奥格兰德天主教大学(PUCRS))