Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring
Confident RAG: 通过多嵌入和置信度评分提升LLM在数学问题回答中的性能
Shiting Chen, Zijian Zhao, Jinsong Chen
机构
*
Faculty of Education, The University of Hong Kong(香港大学教育学院)
;
Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology(香港科学与技术大学土木与环境工程系)
Less Context, Same Performance: A RAG Framework for Resource-Efficient LLM-Based Clinical NLP
Satya Narayana Cheetirala, Ganesh Raut, Dhavalkumar Patel, Fabio Sanatana, Robert Freeman, Matthew A Levin, Girish N. Nadkarni, Omar Dawkins, Reba Miller, Randolph M. Steinhagen, Eyal Klang, Prem Timsina
机构
*
Institute for Healthcare Delivery Science(医疗保健交付科学研究所)
;
Department of Anesthesiology, Perioperative and Pain Medicine(麻醉学、围手术期医学和疼痛医学系)
;
Hasso Plattner Institute for Digital Health(数字健康哈索·platzer研究所)
;
Windreich Department of Artificial Intelligence and Human Health, Mount Sinai Medical Center, NY, USA(人工智能与人类健康威德里奇部门,辛辛那提医学中心,纽约,美国)
;
Department of Surgery(外科系)
;
Department of Surgery, Senior Quality Data Analyst – ISM(外科系,高级质量数据分析员 – ISM)
;
Department of Surgery, Division of Quality and Patient Safety, All at Icahn School of Medicine at Mount Sinai, NY, USA(外科系,质量与患者安全分会,全部在辛辛那提医学院,纽约,美国)
An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments and Analysis]
对PostgreSQL数据库系统中滤波无关向量搜索的深入研究:[实验与分析]
Duo Lu, Helena Caminal, Manos Chatzakis, Yannis Papakonstantinou, Yannis Chronis, Vaibhav Jain, Fatma Özcan
机构
*
Brown University Providence Rhode Island USA
;
Google Sunnyvale California USA
;
Google San Diego California USA
;
ETH Zurich \& Google Zurich Switzerland
;
Google Bangalore India
;
Brown University
;
Google
;
ETH Zurich \& Google
CommentsPresented at ICML 2025 VecDB Workshop; an extended version appeared in ACM SIGMOD 2025 ('Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art')
Comments18 pages, accepted by ICDE 2026. Due to submission limitation for ICDE 2026 (i.e., maximum 6 submissions per author), Lei Chen and Xuemin Lin are not included as authors