Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection
我们是否仍然需要人在回路中?比较主动学习中用于敌意检测的人类与LLM标注
Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein, Hinrich Schütze
机构
*
Center for Information and Language Processing, LMU Munich(慕尼黑大学信息与语言处理中心)
;
Department of Computer Science, University of Copenhagen(哥本哈根大学计算机科学系)
;
Munich Center for Machine Learning(慕尼黑机器学习中心)
Comments23 pages, 6 figures, 3 tables, LaTeX; added missing proof for Proposition 3, typos corrected, updated example 1 to have positive values for the Sankey
Journal refMohamed, Amr, Maram Assi, and Mariam Guizani. "The impact of llm-assistants on software developer productivity: A systematic review and mapping study." ACM Transactions on Software Engineering and Methodology (2026)
Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content
LLM的隐式身份技术:跨数据集、模型和生成内容的指纹识别与水印
Bing Liu, Shunping Wang, Yufan Zhu, Xinyi Yu, Jing Huang, Linkang Du, Hongbin Pei, Wei Luo
机构
*
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)
专题命中
评测与基准
:LLM(title_cn,summary_cn);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG
CommentsAccepted by IJCAI-ECAI 2026. 11 pages, 1 figure. Survey and taxonomy of LLM fingerprinting and watermarking for identity, provenance, generated-content attribution, and asset protection
"LLM Agent Performance" Is Not a Single Evaluation Target
基于LLM的智能体评估统一框架的必要性
Pengyu Zhu, Li Sun, Philip S. Yu, Sen Su
机构
*
Beijing University of Posts and Telecommunications(北京邮电大学)
;
University of Illinois Chicago(伊利诺伊大学芝加哥分校)
;
Chongqing University of Posts and Telecommunications(重庆邮电大学)
CommentsThis version of the contribution has been accepted for publication at ICAI 2026, after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections
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
Catalyst-Agent: Autonomous heterogeneous catalyst screening with an LLM Agent
Catalyst-Agent:基于LLM Agent的自主异质催化剂筛选
Achuth Chandrasekhar, Janghoon Ock, Amir Barati Farimani
机构
*
Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA(卡内基梅隆大学机械工程系,匹兹堡,PA 15213,USA)
;
Department of Chemical and Biomolecular Engineering, University of Nebraska--Lincoln, Lincoln, NE 68588, USA(内布拉斯加大学林肯分校化学与生物分子工程系,林肯,NE 68588,USA)