English(EN)AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering
新的RAG研究优化检索、置信度和组件基准测试
作者PulseAugur 编辑部·[10 个来源]·
多篇研究论文探讨了检索增强生成（RAG）的进展，以提高其效率和可靠性。一种方法“在获取前了解”（Know Before You Fetch）通过基于置信度信号决定是进行闭卷回答、检索最小上下文还是检索完整上下文来校准检索预算。另一种方法AB-RAG使用一种无需训练的框架来估计答案置信度，并在预算内自适应地检索证据，显示出对正确和错误答案的可靠区分。GeoRAG将上下文选择重塑为一个优化问题，通过生成多样化的子查询并确保全面的信息覆盖来更好地处理复杂查询。此外，XRAG提供了一个用于RAG组件基准测试的开源框架，而其他研究则探讨了嵌入空间几何对检索稳定性的影响，并分析了RAG系统的敏感性和鲁棒性。
AI
arXiv cs.CL
TIER_1English(EN)·Zhe Dong (University of Maine at Presque Isle), Fang Qin (Stanford University), Manish Shah (Independent Researcher), Yicheng Wang (Independent Researcher)·
arXiv:2606.29959v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows the answer, and it can be harmful when irrelevant or partially relevant passages d…
arXiv:2606.29090v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This was…
arXiv:2606.29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks down for complex queries, such as multi-hop or ambiguous questions, where top-k sel…
arXiv cs.AI
TIER_1English(EN)·Qili Zhang, Qianren Mao, Yangyifei Luo, Yashuo Luo, Hanwen Hao, Zhilong Cao, Weifeng Jiang, Zhijun Chen, Junnan Liu, Feng Yan, Xiaolong Wang, Jinlong Zhang, Zhenting Huang, Zhixing Tan, Jie Sun, Bo Li, Jianxin Li, Philip S. Yu·
arXiv:2412.15529v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output is not only contextually relevant but als…
arXiv:2606.28330v1 Announce Type: cross Abstract: Embedding-based retrieval systems rely on the assumption that geometric proximity in highdimensional representation spaces reflects semantic relevance. However, high-dimensional geometry induces concentration phenomena that can re…
arXiv:2606.28337v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are often evaluated using final answer accuracy, even though their failures can originate from preprocessing, retrieval, context packing, or generation. This paper presents a controlled…
arXiv cs.AI
TIER_1English(EN)·Ian van Dort (University of Amsterdam), Maria Heuss (University of Amsterdam)·
arXiv:2606.28358v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often using inline citations for verifiability. However, the faithfulness o…
Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows the answer, and it can be harmful when irrelevant or partially relevant passages distract the reader. We formulate adaptive RAG as c…
Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single query embedding. This assumption breaks down for complex queries, such as multi-hop or ambiguous questions, where top-k selection tends to over-cover one semantic aspect whi…
Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard on…
