English
Related papers

Related papers: Enhancing Retrieval Performance: An Ensemble Appro…

200 papers

Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation. Most previous…

Computation and Language · Computer Science 2025-01-14 Junlong Liu , Yue Ma , Ruihui Zhao , Junhao Zheng , Qianli Ma , Yangyang Kang

Contextual information in search sessions is important for capturing users' search intents. Various approaches have been proposed to model user behavior sequences to improve document ranking in a session. Typically, training samples of…

Information Retrieval · Computer Science 2022-09-16 Yutao Zhu , Jian-Yun Nie , Yixuan Su , Haonan Chen , Xinyu Zhang , Zhicheng Dou

Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…

Information Retrieval · Computer Science 2020-10-21 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Min Zhang , Shaoping Ma

Large Language Models (LLMs) face significant challenges in specialized domains like law, where precision and domain-specific knowledge are critical. This paper presents a streamlined two-stage framework consisting of Retrieval and…

Information Retrieval · Computer Science 2025-07-22 Van-Hoang Le , Duc-Vu Nguyen , Kiet Van Nguyen , Ngan Luu-Thuy Nguyen

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Computation and Language · Computer Science 2026-04-29 Jerry Huang , Siddarth Madala , Risham Sidhu , Cheng Niu , Hao Peng , Julia Hockenmaier , Tong Zhang

Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…

Information Retrieval · Computer Science 2023-11-28 Abhijit Anand , Jurek Leonhardt , Jaspreet Singh , Koustav Rudra , Avishek Anand

Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system's goal is to find the most appropriate response, rather than…

Computation and Language · Computer Science 2018-10-09 Denis Fedorenko , Nikita Smetanin , Artem Rodichev

Hard negatives are essential for training effective retrieval models. Hard-negative mining typically relies on ranking documents using cross-encoders or static embedding models based on similarity metrics such as cosine distance. Hard…

Information Retrieval · Computer Science 2025-12-23 Aarush Sinha , Pavan Kumar S , Roshan Balaji , Nirav Pravinbhai Bhatt

Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models. Existing pipelines often…

Information Retrieval · Computer Science 2025-11-25 Roksana Goworek , Olivia Macmillan-Scott , Eda B. Özyiğit

Text embedding models have been popular for information retrieval applications such as semantic search and Question-Answering systems based on Retrieval-Augmented Generation (RAG). Those models are typically Transformer models that are…

Information Retrieval · Computer Science 2025-02-10 Gabriel de Souza P. Moreira , Radek Osmulski , Mengyao Xu , Ronay Ak , Benedikt Schifferer , Even Oldridge

"High Quality Related Search Query Suggestions" task aims at recommending search queries which are real, accurate, diverse, relevant and engaging. Obtaining large amounts of query-quality human annotations is expensive. Prior work on…

Information Retrieval · Computer Science 2021-08-11 Praveen Kumar Bodigutla

Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker…

Information Retrieval · Computer Science 2025-12-19 Tejul Pandit , Sakshi Mahendru , Meet Raval , Dhvani Upadhyay

In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic empirical framework for…

Modern ML systems increasingly augment input instances with additional relevant information to enhance final prediction. Despite growing interest in such retrieval-augmented models, their fundamental properties and training are not well…

Machine Learning · Computer Science 2024-08-29 Soumya Basu , Ankit Singh Rawat , Manzil Zaheer

Embedding-based retrieval (EBR) methods are widely used in modern recommender systems thanks to its simplicity and effectiveness. However, along the journey of deploying and iterating on EBR in production, we still identify some fundamental…

Information Retrieval · Computer Science 2023-02-07 Yuan Zhang , Xue Dong , Weijie Ding , Biao Li , Peng Jiang , Kun Gai

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric…

Information Retrieval · Computer Science 2021-01-22 Luís Borges , Bruno Martins , Jamie Callan

To support complex search tasks, where the initial information requirements are complex or may change during the search, a search engine must adapt the information delivery as the user's information requirements evolve. To support this…

Information Retrieval · Computer Science 2021-05-24 Jianghong Zhou , Eugene Agichtein

Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model.…

Information Retrieval · Computer Science 2024-05-29 Revanth Gangi Reddy , Pradeep Dasigi , Md Arafat Sultan , Arman Cohan , Avirup Sil , Heng Ji , Hannaneh Hajishirzi

Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning…

Computation and Language · Computer Science 2024-04-16 Zepeng Ding , Wenhao Huang , Jiaqing Liang , Deqing Yang , Yanghua Xiao

Ranking models play a crucial role in enhancing overall accuracy of text retrieval systems. These multi-stage systems typically utilize either dense embedding models or sparse lexical indices to retrieve relevant passages based on a given…

Information Retrieval · Computer Science 2024-09-13 Gabriel de Souza P. Moreira , Ronay Ak , Benedikt Schifferer , Mengyao Xu , Radek Osmulski , Even Oldridge