Climate change is a major socio-scientific issue shapes public decision-making and policy discussions. As large language models (LLMs) increasingly serve as an interface for accessing climate knowledge, whether existing benchmarks reflect user needs is critical for evaluating LLM in real-world settings. We propose a Proactive Knowledge Behaviors Framework that captures the different human-human and human-AI knowledge seeking and provision behaviors. We further develop a Topic-Intent-Form taxonomy and apply it to analyze climate-related data representing different knowledge behaviors. Our results reveal a substantial mismatch between current benchmarks and real-world user needs, while knowledge interaction patterns between humans and LLMs closely resemble those in human-human interactions. These findings provide actionable guidance for benchmark design, RAG system development, and LLM training. Code is available at https://github.com/OuchengLiu/LLM-Misalign-Climate-Change.
Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Microsoft Research Asia(微软亚洲研究院);Department of Sociology, Zhejiang University(浙江大学社会学系)
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
AIRI;MTUCI;Algoverse AI Research;Skoltech;Yandex School of Data Analysis;MSU;ISP RAS Research Center for Trusted Artificial Intelligence;Yerevan State University
An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
Department of Archeology and Museology, Shanghai University(考古与博物馆学系,上海大学);National Collaborative Research Center for Revolutionary Cultural Heritage at Memorial of the First CPC National Congress & Shanghai University(革命文化遗产国家联合研究中心,中共一大会址纪念馆与上海大学);School of Management, Shanghai University(管理学院,上海大学);Nanyang Technological University(南洋理工大学)
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
International Institute of Information Technology, Hyderabad(国际信息研究所,海得拉巴);Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi(Mohamed bin Zayed人工智能大学,阿布扎比)
CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs
Worcester Polytechnic Institute(沃斯特理工学院);Aragon Institute of Engineering Research(阿拉贡工程研究院);Pyrenean Institute of Ecology (IPE-CSIC)(比利牛斯生态研究院(IPE-CSIC))
Misalignment of LLM-Generated Personas with Human Perceptions in Low-Resource Settings
Computational Story Lab(计算故事实验室);Vermont Complex Systems Institute(佛罗里达复杂系统研究所);Vermont Advanced Computing Center(佛罗里达高级计算中心);Department of Mathematics and Statistics(数学与统计学系);Department of Computer Science University of Vermont(佛罗里达大学计算机科学系);Santa Fe Institute(圣菲研究所)
LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Fudan University(复旦大学);University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学)
Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research(阿尔弗雷德·魏格纳研究所,亥姆霍兹极地与海洋研究中心);Politecnico di Torino(都灵理工大学);University of Bremen(不来梅大学)
AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents
Department of Computer Science(计算机科学系);University of Oxford(牛津大学);Institute of Intelligent Systems and Robotics(智能系统与机器人研究所);Sorbonne Université(索邦大学);The Leverhulme Centre for the Future of Intelligence(未来智能中心);University of Cambridge(剑桥大学);Independent Researcher(独立研究者);Department of Computer Science and Technology(计算机科学与技术系);Department of Engineering(工程系)
Preemptive Detection and Correction of Misaligned Actions in LLM Agents
Ubiquitous Knowledge Processing Lab, Department of Computer Science, TU Darmstadt(图宾根大学计算机科学系);National Research Center for Applied Cybersecurity ATHENE, Germany(德国应用网络安全国家研究中心ATHENE);Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute, Queen’s University, Canada(加拿大女王大学电气与计算机工程系及创新实验室研究院)
Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain
LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
University of Central Florida(中央佛罗里达大学);University of Maryland, College Park(马里兰大学 College Park 分校);Princeton University(普林斯顿大学);Capital One(Capital One 公司)
"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)