When Direct Prediction Fails: Evidence from LLM-Based Misinformation Risk Evaluation
超越表面判断:LLM生成虚假信息的人类基础风险评估
Zonghuan Xu, Xiang Zheng, Yutao Wu, Xingjun Ma
机构
*
Institute of Trustworthy Embodied AI, Fudan University(复旦大学可信具身人工智能研究所)
;
Shanghai Key Laboratory of Multimodal Embodied AI(上海市多模态具身人工智能重点实验室)
;
City University of Hong Kong(香港城市大学)
;
Deakin University(迪肯大学)
Comments9 pages, 1 figure. Substantially revised and reorganized version of arXiv:2604.06820 based on the same study and data; adds stricter participant filtering, held-out prediction analyses, and additional robustness checks
DSBench: A Comprehensive Benchmark for Evaluating External and In-Cabin Risks
DSBench:用于评估外部和车内风险的综合基准测试
Xianhui Meng, Yuchen Zhang, Zhijian Huang, Zheng Lu, Ziling Ji, Yandan Lin, Yaoyao Yin, Hongyuan Zhang, Wei Zhou, Guangfeng Jiang, Li Zhang, Long Chen, Hangjun Ye, Jun Liu, Xiaoshuai Hao
机构
*
University of Science and Technology of China(中国科学技术大学)
;
Georgia Institute of Technology(佐治亚理工学院)
;
Xiaomi EV(小米电动车)
;
Fudan University(复旦大学)
;
Xidian University(西安电子科技大学)
;
South China University of Technology(华南理工大学)
;
The University of Hong Kong(香港大学)
Explaining and Tuning Transformer-based LLMs in Arithmetic Tasks with Human Strategies
用人类策略解释和调整基于Transformer的语言模型在算术任务中的表现
Luyu Qiu, Jianing Li, Hwanhee Kim, Xiaoyong Wei, Yueyuan Zheng, Janet Hsiao, Lei Chen
机构
*
The Hong Kong University of Science and Technology(香港科技大学)
;
The Hong Kong Polytechnic University(香港理工大学)
;
University of California, Berkeley(加州大学伯克利分校)
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
截断盲区:解码策略如何系统性地排除人类样式的令牌选择
Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann, Matthias Aßenmacher
机构
*
Department of Statistics, Ludwig Maximilian University, Munich, Germany(统计系,路德维希-马克西米利安大学,慕尼黑,德国)
;
Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心(MCML))
机构
*
Washington University in Saint Louis(华盛顿大学圣路易斯分校)
;
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)
;
State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI)