AI 大模型

RAG / 检索增强生成

检索增强生成、向量检索、知识库问答和面向大模型的搜索系统。

2026-03-12 至 2026-03-12 共收录 3 篇信号源：cs.IR, cs.CL, cs.AI, cs.DB

1. RAG评测 3 篇

2603.09704 2026-03-12 cs.CL 83%

Evaluation of LLMs in retrieving food and nutritional context for RAG systems

对LLMs在RAG系统中检索食物和营养上下文的评估

Maks Požarnik Vavken, Matevž Ogrinc, Tome Eftimov, Barbara Koroušić Seljak

机构 * Department of Computer Systems Institute "Jožef Stefan"（计算机系统研究所（Jožef Stefan）部门）

专题命中 RAG评测：RAG(title,abstract)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结本文评估了LLMs在RAG系统中检索食物和营养信息的能力，发现其在可表达约束下表现良好，但在复杂约束下存在局限。

Comments This is the preprint for our conference paper for IEEE International Conference on Big Data

2511.03782 2026-03-12 cond-mat.supr-con cond-mat.str-el cs.AI 70%

Expert Evaluation of LLM World Models: A High-$T_c$ Superconductivity Case Study

专家评估LLM世界模型：一个高温超导体案例研究

Haoyu Guo, Maria Tikhanovskaya, Paul Raccuglia, Alexey Vlaskin, Chris Co, Daniel J. Liebling, Scott Ellsworth, Matthew Abraham, Elizabeth Dorfman, N. P. Armitage, Chunhan Feng, Antoine Georges, Olivier Gingras, Dominik Kiese, Steven A. Kivelson, Vadim Oganesyan, B. J. Ramshaw, Subir Sachdev, T. Senthil, J. M. Tranquada, Michael P. Brenner, Subhashini Venugopalan, Eun-Ah Kim

专题命中 RAG评测：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI

AI总结本文通过专家评估LLM在高温超导领域的问题回答能力，发现基于RAG的系统在全面性和证据支持方面优于封闭模型。

Comments (v1) 9 pages, 4 figures, with 7-page supporting information. Accepted at the ICML 2025 workshop on Assessing World Models and the Explorations in AI Today workshop at ICML'25

Journal ref Proceedings of the National Academy of Sciences 123, e2533676123 (2026)

2603.10570 2026-03-12 cs.CL 57%

End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering

端到端对话机器人评估与自适应推理和不确定性过滤

Nhi Dang, Tung Le, Huy Tien Nguyen

专题命中 RAG评测：retrieval augmented generation(abstract)；分类 cs.CL

AI总结本研究提出一种端到端自动评估器，通过生成问答对和置信度过滤，实现对话机器人评估的自动化和可扩展性。