RAG / 检索增强生成

Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery

空间增强的检索增强生成用于步行性和城市探索

Maddalena Amendola, Chiara Pugliese, Raffaele Perego, Chiara Renso

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)；RAG(abstract)；分类 cs.IR

AI总结 WalkRAG通过空间增强的检索增强生成框架，结合信息检索与空间推理，为用户提供步行性城市探索的推荐服务。

Factuality and Transparency Are All RAG Needs! Self-Explaining Contrastive Evidence Re-ranking

事实性与透明性是RAG所需的一切！自解释对比证据重排序

Francielle Vargas, Daniel Pedronette

机构 * São Paulo State University（圣保罗州立大学） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；分类 cs.CL

AI总结 CER通过对比学习和生成归因理由，提升检索准确性并减少幻觉风险，提供透明的证据检索。

Comments This work was presented as a poster at the Applied Social Media Lab during the 2025 Synthesizer & Open Showcase at the Berkman Klein Center for Internet & Society at Harvard University

MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems

MetaSynth: 从黑盒系统中的隐式反馈生成多智能体元数据

Shreeranjani Srirangamsridharan, Ali Abavisani, Reza Yousefi Maragheh, Ramin Giahi, Kai Zhao, Jason Cho, Sushant Kumar

专题命中 检索器与排序 ：retrieval-augmented generation(abstract)；分类 cs.IR

AI总结 MetaSynth通过多智能体检索增强生成框架，利用黑盒系统中的隐式反馈优化元数据生成，提升了CTR和点击率表现。

Comments IEEE Big Data 2025