Neural networks with deep architectures have demonstrated significant performance improvements in computer vision, speech recognition, and natural language processing. The challenges in information retrieval (IR), however, are different from these other application areas. A common form of IR involves ranking of documents--or short passages--in response to keyword-based queries. Effective IR systems must deal with query-document vocabulary mismatch problem, by modeling relationships between different query and document terms and how they indicate relevance. Models should also consider lexical matches when the query contains rare terms--such as a person's name or a product model number--not seen during training, and to avoid retrieving semantically related but irrelevant results. In many real-life IR tasks, the retrieval involves extremely large collections--such as the document index of a commercial Web search engine--containing billions of documents. Efficient IR methods should take advantage of specialized IR data structures, such as inverted index, to efficiently retrieve from large collections. Given an information need, the IR system also mediates how much exposure an information artifact receives by deciding whether it should be displayed, and where it should be positioned, among other results. Exposure-aware IR systems may optimize for additional objectives, besides relevance, such as parity of exposure for retrieved items and content publishers. In this thesis, we present novel neural architectures and methods motivated by the specific needs and challenges of IR tasks.
PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism
College of Computer Science, Beijing university of technology, Beijing, China（北京理工大学计算机科学学院）；Department of Computer Science and Engineering, Bologna University, Bologna, Italy（博洛尼亚大学计算机科学与工程系）
Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depth
Microsoft（微软公司）；Institute for Clarity in Documentation（文档清晰研究所）；Inria Paris-Rocquencourt（巴黎-罗克奎恩特研究所）；Rajiv Gandhi University（拉贾夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）
HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
Peking University（北京大学）；Center for LLM, Institute for Advanced Algorithms Research（大模型中心，高级算法研究所）；Huazhong University of Science and Technology（华中科技大学）
Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；WeChat AI, Tencent（腾讯微信AI）；Hong Kong University of Science and Technology（香港科学与技术大学）
Evaluating Stochastic Rankings with Expected Exposure
我们引入了\emph{expected exposure}的概念，作为平均关注度排名项目收到来自用户的重复样本相同的查询。此外，我们主张采用平等的预期曝光原则：给定一个固定的信息需求，没有一个项目的预期曝光应该比相同相关性等级的任何其他项目更多或更少。我们认为，这一原则是可取的许多检索目标和场景，包括主题多样性和公平的排名。利用现有的检索指标的用户模型，我们提出了一个通用的评估方法，基于预期的曝光和绘制连接到相关的指标在信息检索评估。重要的是，这种方法放松了经典的信息检索假设，允许系统响应于查询产生一个\emph{distribution over rankings}，而不是一个单一的固定排名。我们研究的行为，预期的曝光度量和随机排名在各种信息访问条件，包括\emph{ad hoc}检索和推荐。我们相信，使用随机化来测量和优化预期的暴露度量为检索算法的开发和进步开辟了一个新的领域。
University of Science and Technology of China（中国科学技术大学）；University of Electronic Science and Technology of China（电子科技大学）；Lanzhou University（兰州大学）；University of Glasgow（格拉斯哥大学）；City University of Hong Kong（香港城市大学）；The Ohio State University（俄亥俄州立大学）
Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations
V. A. Trapeznikov ICS RAS Russian Biotechnological University (ROSBIOTECH)（Trapeznikov ICS 俄罗斯科学院俄罗斯生物技术大学）；Russian Biotechnological University (ROSBIOTECH)（俄罗斯生物技术大学）
Graph-Aware Late Chunking for Retrieval-Augmented Generation in Biomedical Literature
Methodological Implementation Research, Ottawa Hospital Research Institute（方法学实施研究，渥太华医院研究所在职）；School of Engineering Design and Teaching Innovation, University of Ottawa（工程设计与教学创新学院，渥太华大学）
