English(EN) Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG

新研究探索RAG系统的自适应检索

作者 PulseAugur 编辑部 · [3 个来源] · 2026-05-29 12:08

两篇新研究论文探讨了检索增强生成（RAG）系统的自适应检索策略。一篇论文介绍了“检索器投资组合”，一种选择多样化检索器以覆盖各种查询类型的方法，提高了准确性并降低了延迟。另一篇论文专注于金融RAG，开发了一个根据市场反馈和事件类型调整其检索层的系统，以提高预测准确性和投资组合表现。 AI

影响这些自适应RAG技术可以提高AI系统在从金融预测到一般问答等各种应用中的准确性和效率。

排序理由两篇在arXiv上发表的学术论文，详细介绍了RAG系统的新方法。

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

arXiv cs.CL TIER_1 English(EN) · Zijie Zhao, Roy E. Welsch · 2026-06-01 04:00

Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG

arXiv:2605.31201v1 Announce Type: new Abstract: Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source depends on event type, forecast horizon, and market context. We study news-trig…
arXiv cs.LG TIER_1 English(EN) · Miltiadis Stouras, Vincent Cohen-Addad, Silvio Lattanzi, Ola Svensson · 2026-06-01 04:00

Retriever Portfolios: A Principled Approach to Adaptive RAG

arXiv:2605.31176v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems typically rely on a single retriever and a single set of hyperparameters, despite facing highly heterogeneous queries that range from simple factoid questions to complex multi-hop reasoni…
arXiv cs.CL TIER_1 English(EN) · Roy E. Welsch · 2026-05-29 12:08

学习信任谁：面向事件驱动金融RAG的基于市场反馈的自适应检索（针对冻结LLMs）

Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source depends on event type, forecast horizon, and market context. We study news-triggered event-impact prediction as a point-in-time…