论文

提出知识对齐的多跳检索器 KAMR，区分受 query 强约束的 anchor triplet 和弱对齐但在结构上与 anchor 相连的 connected triplet，持续提升多跳检索及下游问答性能。A knowledge-aligned multi-hop retriever, KAMR, which distinguishes anchor triplets that are strongly constrained by the query from connected triplets that are weakly aligned yet structurally linked to the anchors, which consistently improves multi-hop retrieval and downstream question answering performance.

提出 DualG-MRAG，一种面向多模态 RAG 的双层框架，解耦 Macro-reasoning 与 Micro-matching Graph 两类图结构，通过分离全局结构推理与细粒度证据匹配来抑制检索噪声，并引入动态规划解码机制，从 GNN 前向过程中直接提取显式推理路径。DualG-MRAG is proposed, a Dual-tier framework that introduces a decoupled architecture comprising Macro-reasoning and Micro-matching Graphs for Multimodal RAG to suppress retrieval noise by isolating global structural reasoning from fine-grained evidence matching, and introduces a dynamic programming decoding mechanism that extracts explicit reasoning paths directly from the GNN's forward pass.

引入一个基于 GLM 的 retriever，并在单跳与多跳 RAG 场景下对比分析 GLM-based、GNN-based 与传统向量检索 retriever 的相对优势，指出微调后的 GLM retriever 具有更好的跨域泛化能力。This work introduces a GLM-based retriever and investigates the comparative strengths of GLM-based, GNN-based, and traditional vector-search-based retrievers in single- and multi-hop RAG settings, and suggests that finetuned GLM retrievers generalize better out of domain.

提出 ConMem，一个面向 LLM 辅助设备巡检的贡献感知 memory 框架，支持人在环的早期风险筛查，并在受限 memory 预算下保留高价值证据。This work proposes ConMem, a contribution-aware memory framework for LLM-assisted equipment inspection, supporting a human-in-the-loop early-risk screening system and retaining high-value evidence under a constrained memory budget.

OptGraph 是首个引入 GraphRAG 的优化 agentic workflow，首次将可复用经验构建为类型化 graph，刻画建模模式、问题形式化、实现细节与错误修正之间的关系。OptGraph is the first optimization agentic workflow that introduces graph retrieval-augmented generation (GraphRAG) and first constructs reusable experience as a typed graph, capturing the relationships among modeling patterns, problem formalization, implementation details, and error corrections.

提出统一框架，融合时频图结构学习与协变量感知的表示融合，证实其在建模选择性变量交互、利用协变量提升预测精度方面的有效性。This work proposes a unified framework integrating time–frequency graph structure learning with covariate-aware representation fusion, confirming its effectiveness in modeling selective variable interactions and leveraging covariates for improved forecasting accuracy.

提出Hypothetical Prompt Embeddings (HyPE)，将假设内容的生成从查询阶段前移到索引阶段，把检索转化为问题-问题匹配任务，无需运行时合成答案生成。This work proposes Hypothetical Prompt Embeddings (HyPE), a framework that shifts the generation of hypothetical content from query time to the indexing phase, and transforms retrieval into a question-question matching task, bypassing the need for runtime synthetic answer generation.

结果表明，DEFRAG 缩小了 SLM 与 LLM 之间的精度差距，同时相比集中式服务，成本降低高达 98.4%，峰值吞吐量提升高达 97.8%，证明了 DEFRAG 在边缘实现 LLM 服务普惠化的潜力。Results show that DEFRAG narrows the SLM–LLM accuracy gap, while reducing cost by up to 98.4% and increasing peak throughput by up to 97.8% over centralized services, demonstrating the potential of DEFRAG for democratized LLM services at the edge.

TEngineDB-V通过将全局段解耦索引物化为关系表，使向量搜索成为Tencent OLAP引擎的一等分析原语，消除scatter-gather执行、降低放大效应，并支持原生存储优化。TEngineDB-V makes vector search a first-class analytical primitive in Tencent's OLAP engine through a global segment-decoupled index materialized as relational tables, eliminating scatter-gather execution, reducing amplification, and enabling native storage optimizations.

UEmbed (Unified Embedding)是一种decoder-only多模态嵌入模型，在单次因果前向中同时产出稀疏词项与稠密表示，提供新范式：在单一模型中统一稠密与稀疏嵌入，并将稀疏检索扩展以统一文本与多模态输入。UEmbed (Unified Embedding), a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one causal forward pass, offers a new paradigm: it unifies dense and sparse embeddings in one model, while further extending sparse retrieval to unify text and multimodal inputs.

STAMPlus 解决了超出单目标预测的三难问题，解耦自回归对话与非自回归 mask 预测，取得 SOTA 分割性能，同时保持通用多模态指令遵循能力，并降低 12 类别延迟。STAMPlus resolves the trilemma beyond single-target prediction, decoupling autoregressive dialogue from non-autoregressive mask prediction and achieves state-of-the-art segmentation performance, preserves general multimodal instruction following, and reduces 12-category latency.

基于欧盟法院判决构建的大规模法律 IR 数据集，支持法律信息检索方法的开发与严格评估，覆盖多种查询-文档粒度（案例对案例、段落对案例、段落对段落检索）。A large-scale legal IR dataset constructed from Court of Justice of the European Union judgments, which supports both the development and rigorous evaluation of legal IR methods, at multiple query-document levels (case-to-case, paragraph-to-case, and paragraph-to-paragraph retrieval).

研究表明在希腊语专业语料上，无参数 BM25 基线优于多个现成的多语言稠密检索模型，并推出首个大规模希腊语 RAG 基准 HERA，同时发布适配模型与基准以支撑未来希腊语 RAG 系统研究。This study shows that a parameter-free BM25 baseline outperforms several off-the-shelf multilingual dense retrieval models on specialist Greek corpora and introduces HERA, the first large-scale Greek benchmark for retrieval-augmented generation, and releases adapted models and benchmark to support future research on Greek-language RAG systems.

配对 MEG 掩蔽实验表明，19 个刺激特征中有 15 个有贡献，其中静音、声音强度、元音和声学起始的影响最大；说明缺乏叙事结构的神经活动相比连贯语音下的活动，可恢复的信息更少。Paired MEG occlusion shows that 15 of 19 stimulus features contribute, with the largest effects for silence, sound intensity, vowels, and acoustic onsets, indicating that activity without narrative structure carries less recoverable information than activity during coherent speech.

本工作提出一种通过引入自注意力来提取可解释句子嵌入的新模型，使用一个二维矩阵表示嵌入，其中矩阵的每一行关注句子的不同部分。A new model for extracting an interpretable sentence embedding by introducing self-attention is proposed, which uses a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence.

提出 READ（Reliable Embedding-free Agentic Document-search）：Agent 通过三种确定性操作——归一化词法搜索、结构导航与有界片段读取——直接读取原始文档，这些操作通过 Model Context Protocol 暴露，使轨迹成为可回放的审计轨迹，而非不透明相似度分数。This work proposes READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations -- normalized lexical search, structural navigation, and bounded span reads -- exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score.

本文提出 Atlas，一个经过精心设计并预训练的检索增强大语言模型，能以极少训练样例学习知识密集型任务，并研究了文档索引内容的影响，表明该索引可便捷地更新。This work presents Atlas, a carefully designed and pre-trained retrieval augmented language model able to learn knowledge intensive tasks with very few training examples, and studies the impact of the content of the document index, showing that it can easily be updated.

本文在低 prefill 延迟约束下优化 Pareto 前沿以最大化精度，提出 CoinRAG（Contextualized Information Nugget KV Cache Reuse for Long-Context RAG），通过 chunk 级上下文无缝拼接其切片化的 KV 表示。This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse for Long-Context RAG), which seamlessly assembles their sliced KV representations with a chunk-level context.

本文提出 Exact Adaptive Hybrid Retrieval（EAHR），将完整列表加权 RRF 定义的有序 Top-K 固定为检索目标，并将通道深度视为请求特定的执行状态，在全部 150 组 query-snapshot 组合中复现了完整列表的有序 Top-20。This work proposes Exact Adaptive Hybrid Retrieval (EAHR), which fixes the ordered Top-$K$ defined by complete-list weighted RRF as the retrieval target and treats channel depth as request-specific execution state and reproduced the complete-list ordered Top-20 in all 150 query-snapshot combinations.

本文通过深度多模态嵌入视觉与自然语言数据，提出了一种用于图文双向检索的模型，并引入结构化的最大间隔目标，使该模型能够显式地跨模态关联片段。This work introduces a model for bidirectional retrieval of images and sentences through a deep, multi-modal embedding of visual and natural language data and introduces a structured max-margin objective that allows this model to explicitly associate fragments across modalities.

本文利用源自 CNN 的同一基础信息重新审视初始搜索与重排序两个检索阶段，显著改进了现有基于 CNN 的识别流水线。This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN, and significantly improves existing CNN-based recognition pipeline.

训练一个紧凑分类器，对被省略的句子按其是否为理解保留文本所必需进行排序，并在推理时无需支撑标注地回插排名靠前的候选，同时优化相关性与指代完整性。A compact classifier is trained to rank omitted sentences by whether they are needed to interpret retained text and reinsert the top-ranked candidates without support annotations at inference, training a compact classifier to optimize both relevance and referential completeness.

本文提出 Factorized Hypothesis Search (FHS)，在多个命名语义维度上维护多个部分解释，以支持结构化查询渲染、多假设检索以及维度级候选验证。This work proposes Factorized Hypothesis Search (FHS), which maintains multiple partial interpretations over named semantic dimensions that support structured query rendering, multi-hypothesis retrieval, and dimension-level candidate verification.

本文提出 KGCaRe，一种将神经检索与基于 LLM 生成 KG 的符号推理相结合的混合方法，在 Vanilla LLM、Code Prompt、Text Prompt、Think-on-Graph、Vanilla RAG 和 HybridContextQA 等 baseline 上 consistently 取得更优表现。KGCaRe is proposed, a hybrid approach that combines neural retrieval with symbolic reasoning over LLM-generated KGs that consistently outperforms existing baselines, including Vanilla LLM, Code Prompt, Text Prompt, Think-on-Graph, Vanilla RAG, and HybridContextQA.

与现有句法语言模型在推理时对众多句法树求边际或在运行时丢弃句法不同，SiPE 以单一句法树为条件，在句法监督与推理成本之间建立了新的 Pareto 前沿。Unlike existing syntactic language models that marginalize over many parses at inference or discard syntax at runtime, SiPE conditions on a single parse, establishing a new Pareto frontier between syntactic supervision and inference cost.

本文提出 DistilVDR，一个 524M 的端到端 VDR 系统，通过逐点余弦对齐损失从一个 8B 视觉-语言教师模型进行双向蒸馏，并以非对称的纯编码器学生模型匹配 VDR 的文本查询与图像-文档输入不对称性，将视觉容量集中于文档端，查询端保持 70M 参数。This work presents DistilVDR, a 524M end-to-end VDR system distilled bilaterally from a single 8B vision-language teacher under a pointwise cosine alignment loss and matches VDR's text-query and image-document input asymmetry with an asymmetric encoder-only student that concentrates visual capacity on the document side and keeps the query side at 70M parameters.

本文提出一种自我知识 RAG 框架，引导 LLM 从专利匹配查询中自主提取关键技术实体并构建层次化本体结构，从而实现查询扩展与精确检索。A self-knowledge RAG framework is proposed that guides LLMs to autonomously extract key technical entities and construct hierarchical ontological structures from patent matching queries, thereby enabling query expansion and precise retrieval.

本文提出一种框架，用于从系统描述自动构建 DML 模型并将其表示为知识图谱 (KG-DML)，以 RAG 和 LLM 作为使能工具。This study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs (KG-DML), using Retrieval-Augmented Generation and Large Language Models as enabling tools.

ParliamentRAG 是一种主题相关的权威模型，根据当前 query 估计每位发言者的权威性，结合职业、教育和此前发言等可解释组件，以应对政治敏感文本中最高频发言者主导、无法按主题专长加权发言者以及引用归属错误的风险。ParliamentRAG is a topic-dependent authority model that estimates each speaker's authority as a function of the current query, combining interpretable components such as profession, education, and previous interventions that addresses risks of dominance of the most frequent speakers, inability to weight speakers according to topical expertise, and citation misattribution in politically sensitive text.

本文将 S2G-RAG 的结构化充分性-缺口判断适配到冻结的 Search-R1 流程中，并在来自 900 个不相交 HotpotQA 问题的 3009 个状态上训练了一个 Qwen3.5-2B judge，以减少检索次数同时广泛保持答案准确性。This work adapts S2G-RAG's structured sufficiency-and-gap judgment to a frozen Search-R1 pipeline and trains a Qwen3.5-2B judge on 3,009 states from 900 disjoint HotpotQA questions to reduce retrieval while broadly preserving answer accuracy.

本文提出 Syfer，一种用于多语言多跳问答的 synthesizer-folding 框架，默认推迟翻译而非直接应用翻译，在保持具有竞争力准确性的同时，在性能与计算成本之间取得良好平衡。The method Syfer is introduced, a synthesizer-folding framework for multilingual multi-hop question answering that defers translation rather than applying it by default and attains competitive accuracy while striking a favourable balance between performance and computational cost.

本文提出 RAGSieve，为每个检测范围构建匹配的参考集合，其构建需要投毒标签、可信语料或训练过程。This work presents RAGSieve, which constructs a reference matched to each detection scope, which requires poison labels, a trusted corpus, or training to be constructed.

对八个法律 RAG 系统在 GDPR 和某国国内民法两个法律语料上的幻觉行为进行细粒度分析，发现含有错误假设的 false-premise 问题在人工编写问题上产生高幻觉率。A fine-grained analysis of hallucination behavior in eight legal RAG systems across two legal corpora, the GDPR and a national civil law, finds that false-premise questions, containing incorrect assumptions that must be rejected, produce high hallucination rates on the manually-drafted questions.

在多个 benchmark 数据集上的实证评估表明，RAEF 在准确率和推理开销方面均优于 RAF，并且与零样本及微调基础模型的全面对比显示，RAEF 在避免微计算负担的同时取得了与微调相当或更优的性能。Empirical evaluation across multiple benchmark datasets demonstrates that RAEF outperforms RAF in both accuracy and inference overhead, and comprehensive comparisons with zero-shot and fine-tuned foundation models show that RAEF achieves competitive or superior performance to fine-tuning while avoiding its computational burden.

提出 GRIP（Grounded Reasoning via Information-Restricted Premises），引入容量不对称：decoder 对 query 保持全维度访问，而检索到的证据则通过一个严苛的随机瓶颈，迫使证据通道仅编码 query 中无法获得的残余信息。GRIP (Grounded Reasoning via Information-Restricted Premises), which imposes capacity asymmetry: the decoder keeps full-dimensional access to the query, while retrieved evidence passes through a severe stochastic bottleneck, which forces the evidence channel to encode only the residual information unavailable from the query.

将文档结构形式化为多模态超图（Multimodal Hypergraph），以超边作为统一语义容器来封装跨文本、图像和表格的多路关联，超越点对点建模，并引入 Anchor-driven Incremental Refinement 机制。This paper formalizes the document structure as a Multimodal Hypergraph, utilizing hyperedges as unified semantic containers to encapsulate multi-way associations across text, images, and tables, thereby transcending point-to-point modeling and introducing an Anchor-driven Incremental Refinement mechanism.