English(EN)Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
新的RAG技术增强LLM信息检索与生成能力
作者PulseAugur 编辑部·[11 个来源]·
研究人员正在开发先进的检索增强生成（RAG）方法，以改进大型语言模型访问和利用信息的方式。一种名为SetwiseEvalKit的方法侧重于整体评估文档集，而非仅仅评估单个相关性，从而提出了一种名为Rubric4Setwise的方法，该方法优化文档选择以获得更好的下游生成效果。另一项开发VizRAG通过整合超图的视觉线索来增强RAG，以利用多模态能力。此外，M-RAG引入了一个语义键值索引层，将检索键与生成载荷分离，提高了效率和准确性，尤其是在令牌限制下。最后，TSGR专为电子商务搜索设计，将业务价值意识融入生成式检索，以提高交易量和GMV。
AI
arXiv:2607.20560v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of tempora…
arXiv cs.CL
TIER_1English(EN)·Yanbin Wei, Yang Chen, Renling Gan, Ziru Liu, Xinyu Fu, Chun Kang, Ning Lu, Rui Liu, Yu Zhang, James Kwok·
arXiv:2607.19830v1 Announce Type: new Abstract: Hypergraph-based RAG systems surpass traditional graph-based approaches by organizing complex n-ary atomic facts among entities, rather than relying solely on binary relationships. Despite the advancements in multimodal large langua…
arXiv:2607.19747v1 Announce Type: new Abstract: As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents in…
Hypergraph-based RAG systems surpass traditional graph-based approaches by organizing complex n-ary atomic facts among entities, rather than relying solely on binary relationships. Despite the advancements in multimodal large language models (MLLMs) with enhanced visual capabilit…
arXiv:2603.26667v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) turns external documents into evidence for large language models. In practice, this is also a data access problem: a system must decide what to index, what to retrieve, and what evidenc…
As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring i…
Generative retrieval (GR) has demonstrated strong promise for industrial e-commerce search by training a single autoregressive model to directly generate the Semantic IDs (SIDs) of target items. However, existing GR systems are primarily optimized for semantic matching and remain…
Generative retrieval (GR) has demonstrated strong promise for industrial e-commerce search by training a single autoregressive model to directly generate the Semantic IDs (SIDs) of target items. However, existing GR systems are primarily optimized for semantic matching and remain…
arXiv cs.AI
TIER_1English(EN)·Mingyue Cheng, Yucong Luo, Jie Ouyang, Qi Liu, Huijie Liu, Li Li, Shuo Yu, Bohou Zhang, Jiawei Cao, Jie Ma, Daoyu Wang, Enhong Chen·
arXiv:2503.10677v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative mo…
<p>331 375 токенов - столько в среднем съедает один global-запрос Microsoft GraphRAG по замерам GraphRAG-Bench (arXiv:2506.05690). Обычный векторный RAG на том же корпусе укладывается в 879. Разница - примерно 377 раз, и оплачивает её твой счёт за API.</p> <p>Обидно другое: на пр…
"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation" A major blind spot just now getting formal treatment: maximizing retrieval relevance can paradoxically surface sycophantic evidence that reinforces hallucinations rather than c…
