排序始终是信息检索研究的核心方向之一。检索与排序模型是网页搜索、开放域问答、企业域问答、文本推荐系统等众多应用的基础。通常这类模型基于包含二元相关性标注的三元组训练，每个三元组由1个正例段落和1个负例段落组成。但在实际应用中，尤其是对大量潜在相关段落进行重排序时，需要对相关性有更精细的理解。尽管通过曝光、点击等用户反馈收集正例较为简单，但从数百万甚至数十亿文档的庞大语料库中筛选合适的负例对难度更大，而生成足量负例对是维持模型高质量的必要条件。现有研究已提出多种从大规模语料中选取合适负例对的方法。本研究聚焦于阐释难负例在交叉编码器（cross-encoder）模型训练过程中的关键作用， specifically旨在解释难负例采样相比随机采样带来的性能提升机制。我们针对具有领域特定上下文的企业数据集，提出了一种鲁棒的难负例挖掘技术，可实现交叉编码器重排序模型的高效训练。本研究为优化检索模型提供了全新视角，最终将影响检索增强生成（Retrieval-Augmented Generation, RAG）、推理与行动智能体（Reasoning and Action Agents, ReAct）等先进大语言模型系统的性能。实验结果表明，通过交叉编码器同时学习相似性与差异性，能够有效提升检索系统的性能。
英文摘要：
Ranking consistently emerges as a primary focus in information retrieval research. Retrieval and ranking models serve as the foundation for numerous applications, including web search, open domain QA, enterprise domain QA, and text-based recommender systems. Typically, these models undergo training on triplets consisting of binary relevance assignments, comprising one positive and one negative passage. However, their utilization involves a context where a significantly more nuanced understanding of relevance is necessary, especially when re-ranking a large pool of potentially relevant passages. Although collecting positive examples through user feedback like impressions or clicks is straightforward, identifying suitable negative pairs from a vast pool of possibly millions or even billions of documents possess a greater challenge. Generating a substantial number of negative pairs is often necessary to maintain the high quality of the model. Several approaches have been suggested in literature to tackle the issue of selecting suitable negative pairs from an extensive corpus. This study focuses on explaining the crucial role of hard negatives in the training process of cross-encoder models, specifically aiming to explain the performance gains observed with hard negative sampling compared to random sampling. We have developed a robust hard negative mining technique for efficient training of cross-encoder re-rank models on an enterprise dataset which has domain specific context. We provide a novel perspective to enhance retrieval models, ultimately influencing the performance of advanced LLM systems like Retrieval-Augmented Generation (RAG) and Reasoning and Action Agents (ReAct). The proposed approach demonstrates that learning both similarity and dissimilarity simultaneously with cross-encoders improves performance of retrieval systems.
Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
Faculty of Computer Science, University of Information Technology, Ho Chi Minh City, Vietnam（信息科技学院计算机科学系，胡志明市，越南）；Faculty of Information Science and Engineering, University of Information Technology, Ho Chi Minh City, Vietnam（信息科技学院信息科学与工程系，胡志明市，越南）；Laboratory of Multimedia Communications, University of Information Technology, Ho Chi Minh City, Vietnam（信息科技学院多媒体通信实验室，胡志明市，越南）；Vietnam National University, Ho Chi Minh City, Vietnam（越南国家大学，胡志明市，越南）
Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval
Central South University（中南大学）；School of Computer Science and Engineering（计算机科学与工程学院）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Artificial Intelligence Laboratory, China Mobile Communication Group Tianjin Co., Ltd.（中国移动通信集团天津有限公司人工智能实验室）；University College London（伦敦大学学院）
IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memory
School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；School of Engineering, Westlake University（西湖大学工学院）；State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人机混合增强智能全国重点实验室、视觉信息与应用国家工程研究中心、人工智能与机器人研究所）
Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval
Southeast University（东南大学）；Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education（教育部复杂工程系统测量与控制重点实验室）；Nanjing Enbo Technology Co., Ltd.（南京恩博科技有限公司）
MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西北工业大学人工智能、光学与电子学院（iOPEN））
