English
Related papers

Related papers: ReFIT: Relevance Feedback from a Reranker during I…

200 papers

Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be…

Information Retrieval · Computer Science 2021-01-22 Luyu Gao , Zhuyun Dai , Jamie Callan

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose…

Computation and Language · Computer Science 2021-08-10 Yuning Mao , Pengcheng He , Xiaodong Liu , Yelong Shen , Jianfeng Gao , Jiawei Han , Weizhu Chen

Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of…

Information Retrieval · Computer Science 2024-01-23 Suchana Datta , Debasis Ganguly , Sean MacAvaney , Derek Greene

Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recent advances in document compression for RAG, we reduce the…

Information Retrieval · Computer Science 2025-05-22 Hervé Déjean , Stéphane Clinchant

The Retrieval Augmented Generation (RAG) framework utilizes a combination of parametric knowledge and external knowledge to demonstrate state-of-the-art performance on open-domain question answering tasks. However, the RAG framework suffers…

Computation and Language · Computer Science 2024-10-25 Kiseung Kim , Jay-Yoon Lee

Commonsense generation aims to generate a realistic sentence describing a daily scene under the given concepts, which is very challenging, since it requires models to have relational reasoning and compositional generalization capabilities.…

Computation and Language · Computer Science 2022-10-24 Xingwei He , Yeyun Gong , A-Long Jin , Weizhen Qi , Hang Zhang , Jian Jiao , Bartuer Zhou , Biao Cheng , SM Yiu , Nan Duan

State-of-the-art Machine Reading Comprehension (MRC) models for Open-domain Question Answering (QA) are typically trained for span selection using distantly supervised positive examples and heuristically retrieved negative examples. This…

Computation and Language · Computer Science 2020-10-22 Srinivasan Iyer , Sewon Min , Yashar Mehdad , Wen-tau Yih

The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating responses. However, due to differences in pre-training data and…

Computation and Language · Computer Science 2025-12-09 Pengyue Jia , Derong Xu , Xiaopeng Li , Zhaocheng Du , Xiangyang Li , Yichao Wang , Yuhao Wang , Qidong Liu , Maolin Wang , Huifeng Guo , Ruiming Tang , Xiangyu Zhao

For multi-stage recommenders in industry, a user request would first trigger a simple and efficient retriever module that selects and ranks a list of relevant items, then the recommender calls a slower but more sophisticated reranking model…

Information Retrieval · Computer Science 2026-05-19 Wenyu Mao , Shuchang Liu , Hailan Yang , Xiaobei Wang , Xiaoyu Yang , Xu Gao , Xiang Li , Lantao Hu , Han Li , Kun Gai , An Zhang , Xiang Wang

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Gregor Geigle , Jonas Pfeiffer , Nils Reimers , Ivan Vulić , Iryna Gurevych

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

Computation and Language · Computer Science 2021-10-04 Chongyang Tao , Jiazhan Feng , Chang Liu , Juntao Li , Xiubo Geng , Daxin Jiang

Advanced relevance models, such as those that use large language models (LLMs), provide highly accurate relevance estimations. However, their computational costs make them infeasible for processing large document corpora. To address this,…

Information Retrieval · Computer Science 2025-05-08 Mandeep Rathee , V Venktesh , Sean MacAvaney , Avishek Anand

With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face…

Information Retrieval · Computer Science 2026-04-10 Jiani Huang , Shijie Wang , Liangbo Ning , Wenqi Fan , Qing Li

Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a Retrieval-Augmented Generation (RAG) system designed to answer questions about S&P 500…

Computation and Language · Computer Science 2026-04-29 Zhiyuan Cheng , Longying Lai , Yue Liu , Kai Cheng , Xiaoxi Qi

As the final stage of recommender systems, re-ranking presents ordered item lists to users that best match their interests. It plays such a critical role and has become a trending research topic with much attention from both academia and…

Information Retrieval · Computer Science 2025-04-08 Qunwei Li , Linghui Li , Jianbin Lin , Wenliang Zhong

Candidate retrieval is a fundamental issue in recommendation system. Given user's recommendation request, relevant candidates need to be retrieved in realtime for subsequent ranking operations. Considering that the retrieval operation is…

Information Retrieval · Computer Science 2019-10-22 Zheng Liu , Yu Xing , Jianxun Lian , Defu Lian , Ziyao Li , Xing Xie

Traditional machine-learned ranking systems for web search are often trained to capture stationary relevance of documents to queries, which has limited ability to track non-stationary user intention in a timely manner. In recency search,…

Information Retrieval · Computer Science 2011-03-22 Taesup Moon , Wei Chu , Lihong Li , Zhaohui Zheng , Yi Chang

Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive…

Information Retrieval · Computer Science 2025-06-24 Lukas Gienapp , Niklas Deckers , Martin Potthast , Harrisen Scells

Pseudo-Relevance Feedback (PRF) utilises the relevance signals from the top-k passages from the first round of retrieval to perform a second round of retrieval aiming to improve search effectiveness. A recent research direction has been the…

Information Retrieval · Computer Science 2023-03-22 Hang Li , Shengyao Zhuang , Ahmed Mourad , Xueguang Ma , Jimmy Lin , Guido Zuccon

Retrieval-augmented generation (RAG) systems combine large language models (LLMs) with external knowledge retrieval, making them highly effective for knowledge-intensive tasks. A crucial but often under-explored component of these systems…

Computation and Language · Computer Science 2025-05-19 Jiashuo Sun , Xianrui Zhong , Sizhe Zhou , Jiawei Han