LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
LLM 的拒绝回答可能既是真实不确定性的体现,也是提示的产物
Zipeng Ling, Shuliang Liu, Yuehao Tang, Junqi Yang, Shenghong Fu, Chen Huang, Kejia Huang, Yao Wan, Zhichao Hou, Xuming Hu
机构
*
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
;
University of Pennsylvania(宾夕法尼亚大学)
;
Huazhong University of Science and Technology(华中科技大学)
;
Nanjing University of Posts and Telecommunications(南京邮电大学)
;
The Hong Kong Polytechnic University(香港理工大学)
专题命中
知识编辑与模型理解
:LLM(title,title_cn);large language model(abstract);language model(abstract);instruction tuning(abstract)
机构
*
Department of XXX, University of YYY, Location, Country(XXX系,YYY大学,地点,国家)
;
School of ZZZ, Institute of WWW, Location, Country(ZZZ学院,WWW研究所,地点,国家)
;
Inria, Paris, France(Inria,巴黎,法国)
专题命中
知识编辑与模型理解
:LLM(title,title_cn);large language model(abstract);language model(abstract);prompting(abstract)
Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal
共识在策略上是不充分的:推理轨迹分歧作为知识表示信号
Michał Wawer, Jarosław A. Chudziak
机构
*
Laboratory of The New Ethos(新伦理实验室)
;
Warsaw University of Technology(华沙理工大学)
;
Institute of Computer Science(计算机科学研究所)
;
Faculty of Electronics and Information Technology(电子与信息技术学院)
Retrieval and competition: how a protein foundation model starts a protein
检索与竞争:蛋白质基础模型如何启动蛋白质
Piotr Jedryszek, Oliver M. Crook
机构
*
Department of Biology, University of Oxford, Oxford, UK(牛津大学生物学系)
;
Kavli Institute for Nanoscience Discovery, University of Oxford, Oxford, UK(牛津大学纳科学发现研究所)
;
Department of Chemistry, University of Oxford, Oxford, UK(牛津大学化学系)
Hybrid Adversarial Defence for Natural Language Understanding Tasks
混合对抗防御用于自然语言理解任务
Manar Abouzaid, Yang Wang, Chenghua Lin, Stuart E. Middleton
机构
*
School of Electronics and Computer Science, University of Southampton, UK(南安普顿大学电子与计算机科学学院)
;
Department of Computer Science, University of Manchester, UK(曼彻斯特大学计算机科学系)
专题命中
知识编辑与模型理解
:large language model(abstract);language model(abstract);分类 cs.CL
BRAINCELL-AID: An Agentic AI Created Brain Cell Type Resource for Community Annotation
BRAINCELL-AID:用于社区注释的由AI代理创建的脑细胞类型资源
Rongbin Li, Wenbo Chen, Zhao Li, Rodrigo Munoz-Castaneda, Jinbo Li, Neha S. Maurya, Arnav Solanki, Huan He, Hanwen Xing, Meaghan Ramlakhan, Zachary Wise, Nelson Johansen, Zhuhao Wu, Hua Xu, Michael Hawrylycz, W. Jim Zheng
机构
*
McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston(德克萨斯大学健康科学中心休斯顿分校麦克威廉斯生物医学信息学学院)
;
Appel Alzheimer’s Disease Research Institute, Feil Family Brain and Mind Research Institute, Weill Cornell Medicine(艾伯神经变性病研究机构、费尔家庭脑与心灵研究机构、韦尔·科恩医学中心)
;
Department of Biomedical Informatics and Data Science, School of Medicine, Yale University(耶鲁大学医学院生物医学信息学与数据科学系)
;
Allen Institute for Brain Science(艾伦脑科学研究所)
专题命中
知识编辑与模型理解
:large language model(abstract);language model(abstract);分类 cs.AI
Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes
利用语义高斯过程改进LVLM中的语义不确定性量化
Joseph Hoche, Andrei Bursuc, David Brellmann, Gilles Louppe, Pavel Izmailov, Angela Yao, Gianni Franchi
机构
*
AMIAD, Pôle Recherche, Palaiseau(AMIAD研究部,Palaiseau)
;
valeo.ai
;
Safran Tech
;
University of Liège(利耶大学)
;
New York University(纽约大学)
;
National University of Singapore(新加坡国立大学)
;
ENSTA Paris(巴黎ENSTA)