English
Related papers

Related papers: On Precomputation and Caching in Information Retri…

200 papers

Retrieval-augmented generation over semi-structured sources such as HTML is constrained by a mismatch between document structure and the flat, sequence-based interfaces of today's embedding and generative models. Retrieval pipelines often…

Information Retrieval · Computer Science 2026-04-24 Mike Rainey , Umut Acar , Muhammed Sezer

Rerankers, typically cross-encoders, are computationally intensive but are frequently used because they are widely assumed to outperform cheaper initial IR systems. We challenge this assumption by measuring reranker performance for full…

Information Retrieval · Computer Science 2025-07-14 Mathew Jacob , Erik Lindgren , Matei Zaharia , Michael Carbin , Omar Khattab , Andrew Drozdov

Performance evaluation of caching systems is an old and widely investigated research topic. The research community is once again actively working on this topic because the Internet is evolving towards new transfer modes, which envisage to…

Networking and Internet Architecture · Computer Science 2013-09-04 G. Bianchi , N. Blefari Melazzi , A. Caponi , A. Detti

Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting evidence, rather than semantic similarity. Motivated by the emergent reasoning abilities…

Information Retrieval · Computer Science 2026-05-04 Yiyang Wei , Tingyu Song , Siyue Zhang , Yilun Zhao

We present a unsupervised semantic search pipeline for the Causality-driven Adhoc Information Retrieval (CAIR-2021) shared task. The CAIR shared task expands traditional information retrieval to support the retrieval of documents containing…

Information Retrieval · Computer Science 2025-03-04 Dhairya Dalal , Sharmi Dev Gupta , Bentolhoda Binaei

The most common approach to implementing data analysis pipelines involves obtaining point estimates from the upstream modules and then treating these as known quantities when working with the downstream ones. This approach is…

Methodology · Statistics 2024-02-19 Erin Lipman , Abel Rodriguez

A wide range of transformer-based language models have been proposed for information retrieval tasks. However, including transformer-based models in retrieval pipelines is often complex and requires substantial engineering effort. In this…

Information Retrieval · Computer Science 2025-04-16 Ferdinand Schlatt , Maik Fröbe , Matthias Hagen

Retrieval-augmented generation (RAG) pipelines have become the de-facto approach for building AI assistants with access to external, domain-specific knowledge. Given a user query, RAG pipelines typically first retrieve (R) relevant…

Human-Computer Interaction · Computer Science 2025-04-21 Quentin Romero Lauro , Shreya Shankar , Sepanta Zeighami , Aditya Parameswaran

Complex information extraction (IE) pipelines assembled by plumbing together off-the-shelf operators, specially customized operators, and operators re-used from other text processing pipelines are becoming an integral component of most text…

Databases · Computer Science 2010-04-12 Anish Das Sarma , Alpa Jain , Philip Bohannon

Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the…

Computation and Language · Computer Science 2024-11-13 Alexandria Leto , Cecilia Aguerrebere , Ishwar Bhati , Ted Willke , Mariano Tepper , Vy Ai Vo

In designing query processing primitives, a crucial design choice is the method for data transfer between two operators in a query plan. As we were considering this critical design mechanism for an in-memory database system that we are…

Databases · Computer Science 2020-02-04 Harshad Deshmukh , Bruhathi Sundarmurthy , Jignesh M. Patel

Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall…

Computation and Language · Computer Science 2024-03-12 Wenqi Jiang , Shuai Zhang , Boran Han , Jie Wang , Bernie Wang , Tim Kraska

Reservoir computing (RC) offers efficient temporal data processing with a low training cost by separating recurrent neural networks into a fixed network with recurrent connections and a trainable linear network. The quality of the fixed…

Emerging Technologies · Computer Science 2021-05-17 John Moon , Wei D. Lu

Many users turn to document retrieval systems (e.g. search engines) to seek answers to controversial questions. Answering such user queries usually require identifying responses within web documents, and aggregating the responses based on…

Computation and Language · Computer Science 2022-06-14 Sihao Chen , Siyi Liu , Xander Uyttendaele , Yi Zhang , William Bruno , Dan Roth

Data is a valuable asset, and sharing it as a product across organizations is key to building comprehensive and useful insights in fields such as science and industry. Before sharing, data often requires transformation to comply with…

Social and Information Networks · Computer Science 2025-03-18 Sepideh Masoudi

We consider information retrieval when the data, for instance multimedia, is coputationally expensive to fetch. Our approach uses "information filters" to considerably narrow the universe of possiblities before retrieval. We are especially…

Information Retrieval · Computer Science 2007-05-23 Neil C. Rowe

In data warehouse and data mart systems, queries often take a long time to execute due to their complex nature. Query response times can be greatly improved by caching final/intermediate results of previous queries, and using them to answer…

Databases · Computer Science 2007-05-23 Prasan Roy , Krithi Ramamritham , S. Seshadri , Pradeep Shenoy , S. Sudarshan

We integrate ir_datasets, ir_measures, and PyTerrier with TIRA in the Information Retrieval Experiment Platform (TIREx) to promote more standardized, reproducible, scalable, and even blinded retrieval experiments. Standardization is…

A major drawback of modern neural OpenIE systems and benchmarks is that they prioritize high coverage of information in extractions over compactness of their constituents. This severely limits the usefulness of OpenIE extractions in many…

Computation and Language · Computer Science 2022-06-13 Farima Fatahi Bayat , Nikita Bhutani , H. V. Jagadish

Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing…