在语言建模领域，带有检索组件的模型已成为解决自然语言处理（NLP）领域若干挑战的有前景方案，这些挑战包括知识 grounding、可解释性和可扩展性。尽管当前主要关注 NLP，我们认为检索增强这一范式可以扩展到更广泛的机器学习（ML）领域，例如计算机视觉、时间序列预测和计算生物学。因此，本工作通过综合 ML 各领域的文献，并以当前文献中缺失的一致符号体系，引入该范式的一个正式框架，即检索增强机器学习（REML）。此外，我们发现，虽然许多研究使用检索组件来增强其模型，但缺乏与基础信息检索（IR）研究的整合。我们通过考察构成 REML 框架的每个组件，弥合了开创性 IR 研究与当代 REML 研究之间的这一差距。最终，本工作的目标是为不同学科的研究者提供一个全面、形式化结构的检索增强模型框架，从而促进未来的跨学科研究。
英文摘要：
In the field of language modeling, models augmented with retrieval components have emerged as a promising solution to address several challenges faced in the natural language processing (NLP) field, including knowledge grounding, interpretability, and scalability. Despite the primary focus on NLP, we posit that the paradigm of retrieval-enhancement can be extended to a broader spectrum of machine learning (ML) such as computer vision, time series prediction, and computational biology. Therefore, this work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature. Also, we found that while a number of studies employ retrieval components to augment their models, there is a lack of integration with foundational Information Retrieval (IR) research. We bridge this gap between the seminal IR research and contemporary REML studies by investigating each component that comprises the REML framework. Ultimately, the goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.
School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Department of Mathematical Sciences, Tsinghua University（清华大学数学科学系）
Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis
Tsinghua University（清华大学）；Nanyang Technological University（南洋理工大学）；The Chinese University of Hong Kong（香港中文大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；University of Cambridge（剑桥大学）
From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development
The Chinese University of Hong Kong, Sha Tin, NT, Hong Kong（香港中文大学）；Université de Montréal, Montréal, Quebéc, Canada（蒙特利尔大学）；McGill University, Montréal, Quebéc, Canada（麦吉尔大学）；Mila - Quebéc AI Institute, Montréal, Quebéc, Canada（魁北克AI研究院）；Huawei Noah’s Ark Lab, Montréal, Quebéc, Canada（华为诺亚实验室）
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Huawei Poisson Lab（华为泊松实验室）；Waseda University（早稻田大学）
PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD)（eBRAIN实验室，工程系，纽约大学阿布扎比分校）；Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute（量子与拓扑系统中心（CQTS），NYUAD研究所）；Department of Computer Science and Engineering, NYU Tandon School of Engineering（计算机科学与工程系，纽约大学坦顿工程学院）
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription
Qatar University（卡塔尔大学）；Birmingham City University（伯明翰城市大学）；Hamad Bin Khalifa University (HBKU)（哈马德·本·哈利法大学）；University of the West of England (UWE)（西英格兰大学）
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Huawei Technologies Co., Ltd.（华为技术有限公司）；City University of Hong Kong（香港城市大学）；School of Cyber Science and Technology, Sun Yat-sen University（中山大学信息科学与技术学院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；The Hong Kong University of Science and Technology（香港科学与技术大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）
