Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts. It indicates that a good IR model can generalize to different tasks and domains. However, previous studies indicate that state-of-the-art neural information retrieval (NIR) models, e.g, pre-trained language models (PLMs) are hard to generalize. Mainly because the end-to-end fine-tuning paradigm makes the model overemphasize task-specific signals and domain biases but loses the ability to capture generalized essential signals. To address this problem, we propose a novel NIR training framework named NIR-Prompt for retrieval and reranking stages based on the idea of decoupling signal capturing and combination. NIR-Prompt exploits Essential Matching Module (EMM) to capture the essential matching signals and gets the description of tasks by Matching Description Module (MDM). The description is used as task-adaptation information to combine the essential matching signals to adapt to different tasks. Experiments under in-domain multi-task, out-of-domain multi-task, and new task adaptation settings show that NIR-Prompt can improve the generalization of PLMs in NIR for both retrieval and reranking stages compared with baselines.
Modular Retrieval for Generalization and Interpretation
新的检索任务不断涌现,促使新的检索模型不断发展。然而,为每个新的检索任务实例化检索模型是资源密集且耗时的,特别是对于采用大规模预训练的语言模型的检索模型。为了解决这个问题,我们转向一种新的检索范式称为模块化检索,其目的是解决新的检索任务,而不是组成多个现有的检索模块。在此基础上,我们提出了一个具有模块化提示微调的检索模型REMP。该方法通过深度提示微调,构造出服从任务属性的检索模块,并通过模块组合得到服从任务属性的检索模型。我们验证,REMP固有的模块化,不仅具有吸引力的概括性和可解释性在初步探索,但也取得了相当的性能,以国家的最先进的检索模型上的zero-shot检索基准。\footnote{Our code is available at \url{https://github.com/FreedomIntelligence/REMOP}}
Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings
University of Primorska(普里莫尔斯卡大学);InnoRenew CoE;Research Centre of the Slovenian Academy of Sciences and Arts(斯洛文尼亚科学与艺术研究院研究中心);The Fran Ramovš Institute(弗兰·拉莫夫什研究所)
Love Me, Love My Label: Rethinking the Role of Labels in Prompt Retrieval for Visual In-Context Learning
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院)
Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
College of Computer Science, Sichuan University(四川大学计算机学院);Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, Chengdu, China(教育部机器学习与产业智能工程研究中心);Deep NeuroCognition Lab, I2R and CFAR, Agency for Science, Technology and Research, Singapore(深度神经认知实验室,I2R和CFAR,科技研究局,新加坡)
UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval
Zhejiang University(浙江大学);Carnegie Mellon University(卡内基梅隆大学);University of Washington(华盛顿大学);Dalian University of Technology(大连理工大学);DAMO Academy, Alibaba Group(阿里巴巴达摩院);Microsoft Research(微软研究院)
MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation
School of Computer Science, Peking University, Beijing, China(北京大学计算机科学学院,北京,中国);School of Information, Renmin University of China, Beijing, China(中国人民大学信息学院,北京,中国)
Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts
Rutgers University(罗格斯大学);Ernest Mario School of Pharmacy(欧内斯特·马里奥药学院);East Brunswick High School(东布伦瑞克高中);Princeton Medical Center(普林斯顿医疗中心);New Jersey Medical School(新泽西医学院);Rutgers Cancer Institute(罗格斯癌症研究所)
Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(信息产业部模式分析与机器智能重点实验室,计算机科学与技术学院,南京航空航天大学);Zhejiang University(浙江大学);Hunan Vanguard Group Corporation Limited(湖南先锋集团有限公司);National University of Singapore(新加坡国立大学)