Tag: Retrieval-Augmented Generation
All the articles with the tag "Retrieval-Augmented Generation".
-
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
本文提出动态参数化RAG框架DyPRAG,通过训练一个轻量级参数翻译器在测试时动态转换文档为参数知识,显著降低成本、提升泛化能力和缓解RAG幻觉问题。
-
LLM-Independent Adaptive RAG: Let the Question Speak for Itself
This paper introduces LLM-independent adaptive retrieval using 27 external information features across 7 groups, achieving comparable QA performance to LLM-based methods on 6 datasets while significantly improving efficiency by eliminating additional LLM calls during inference.
-
SAGE: A Framework of Precise Retrieval for RAG
本文提出SAGE框架,通过语义分割、基于梯度的块选择和LLM自反馈机制,提高RAG系统的检索精度和问答性能,同时显著降低成本。
-
PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset
本文提出 PennyLang 数据集和 RAG/GraphRAG 框架,通过提升 LLM 在 PennyLane 量子代码生成中的准确性和正确性,填补了 AI 辅助量子编程的空白。
-
Synergizing RAG and Reasoning: A Systematic Review
本论文系统综述了检索增强生成(RAG)与推理能力的协同整合,构建了多维分类框架、提供了实用指南,并指出了未来研究方向,以推进RAG系统在复杂任务中的认知能力。