In real-world question-answering (QA) systems, ill-formed questions, such as wrong words, ill word order, and noisy expressions, are common and may prevent the QA systems from understanding and answering them accurately. In order to eliminate the effect of ill-formed questions, we approach the question refinement task and propose a unified model, QREFINE, to refine the ill-formed questions to well-formed question. The basic idea is to learn a Seq2Seq model to generate a new question from the original one. To improve the quality and retrieval performance of the generated questions, we make two major improvements: 1) To better encode the semantics of ill-formed questions, we enrich the representation of questions with character embedding and the recent proposed contextual word embedding such as BERT, besides the traditional context-free word embeddings; 2) To make it capable to generate desired questions, we train the model with deep reinforcement learning techniques that considers an appropriate wording of the generation as an immediate reward and the correlation between generated question and answer as time-delayed long-term rewards. Experimental results on real-world datasets show that the proposed QREFINE method can generate refined questions with more readability but fewer mistakes than the original questions provided by users. Moreover, the refined questions also significantly improve the accuracy of answer retrieval.
Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
Taobao & Tmall Group of Alibaba（阿里巴巴淘宝和天猫集团）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and Networking
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；University of Technology and Design, Singapore（新加坡科技设计大学）；Institute for Infocomm Research, Agency for Science, Technology and Research（新加坡科技研究局信息通信研究院）；Auburn University（奥本大学）；University of Houston（休斯顿大学）；Kyung Hee University（庆熙大学）
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）
R2LED: Equipping Retrieval and Refinement in Lifelong User Modeling with Semantic IDs for CTR Prediction
Xi’an Jiaotong University（西安交通大学）；University of Edinburgh（爱丁堡大学）；Nanyang Technological University（南洋理工大学）；Jilin University（吉林大学）；Zhejiang University of Technology（浙江工业大学）
On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective
CAS Key Lab of Network Data Science and Technology, ICT, CAS（中国科学院计算技术研究所网络数据科学与技术重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Amsterdam（阿姆斯特丹大学）
Generative Universal Multimodal Retrieval with Dual-role Identifiers
Institute of Library, Information and Media Science, University of Tsukuba（筑波大学图书馆、信息与媒体科学研究所）；College of Knowledge and Library Sciences, University of Tsukuba（筑波大学知识与图书馆科学学院）
Existing neural ranking models follow the text matching paradigm, where document-to-query relevance is estimated through predicting the matching score. Drawing from the rich literature of classical generative retrieval models, we introduce and formalize the paradigm of deep generative retrieval models defined via the cumulative probabilities of generating query terms. This paradigm offers a grounded probabilistic view on relevance estimation while still enabling the use of modern neural architectures. In contrast to the matching paradigm, the probabilistic nature of generative rankers readily …
Evaluating Generative Ad Hoc Information Retrieval
Leipzig University（莱比锡大学）；The University of Queensland（昆士兰大学）；Bauhaus-Universität Weimar（魏玛包豪斯大学）；Friedrich-Schiller-Universität Jena（弗里德里希·席勒大学耶拿分校）；University of Kassel（卡塞尔大学）
MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
Visual Intelligence Research Laboratories, NEC Corporation（NEC公司视觉智能研究实验室）；Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究生院）；RIKEN Center for AIP（理化学研究所AIP研究中心）
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft（微软）；Sun Yat-sen University（中山大学）
In a sponsored search engine, generative retrieval models are recently proposed to mine relevant advertisement keywords for users' input queries. Generative retrieval models generate outputs token by token on a path of the target library prefix tree (Trie), which guarantees all of the generated outputs are legal and covered by the target library. In actual use, we found several typical problems caused by Trie-constrained searching length. In this paper, we analyze these problems and propose a looking ahead strategy for generative retrieval models named ProphetNet-Ads. ProphetNet-Ads improves t…
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Pattern Recognition Center, WeChat AI（微信AI模式识别中心）
A common practice for text retrieval is to use an encoder to map the documents and the query to a common vector space and perform a nearest neighbor search (NNS); multi-hop retrieval also often adopts the same paradigm, usually with a modification of iteratively reformulating the query vector so that it can retrieve different documents at each hop. However, such a bi-encoder approach has limitations in multi-hop settings; (1) the reformulated query gets longer as the number of hops increases, which further tightens the embedding bottleneck of the query vector, and (2) it is prone to error prop…
Exploring Training and Inference Scaling Laws in Generative Retrieval
National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）
SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs
University of Electronic Science and Technology of China（电子科技大学）；Tongji University（同济大学）；Singapore Management University（新加坡管理大学）；National University of Singapore（新加坡国立大学）
