提出一种属性知识RAG模式，通过本地与生产环境的混合检索架构，让LLM在受控条件下选择字段，避免幻觉。
Article URL: https://superml.dev/attribute-knowledge-rag-pattern-llm-governed-attributes Comments URL: https://news.ycombinator.com/item?id=48810859 P…
新基准IsoSci通过同构跨领域科学问题，精准区分大模型的推理能力与知识检索水平。
arXiv:2607.01431v1 Announce Type: cross Abstract: We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates rea…
量化RAG系统的先验主导，破解认知盲点，提升知识检索与生成的可信度。
arXiv:2606.23695v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Models in external knowledge, yet curren…
新方法InfoMem用答案条件信息增益训练长上下文记忆代理，大幅提升模型知识检索与记忆能力。
arXiv:2606.03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contex…
基于最新研究的实体链接代理，为问答系统提供精准知识检索与链接能力
arXiv:2508.03865v4 Announce Type: replace Abstract: Some Question Answering (QA) systems rely on knowledge bases (KBs) to provide accurate answers. En…