HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

The volume of scientific literature is growing exponentially, leading to underutilized discoveries, duplicated efforts, and limited cross-disciplinary collaboration. Retrieval-Augmented Generation (RAG) offers a way to assist scientists by improving the factuality of Large Language Models (LLMs) in processing this influx of information. However, scaling RAG to handle millions of articles introduces significant challenges, including the high computational costs associated with parsing documents and embedding scientific knowledge, as well as the algorithmic complexity of aligning these representations with the nuanced semantics of scientific content. To address these issues, we introduce HiPerRAG, a RAG workflow powered by high performance computing (HPC) to index and retrieve knowledge from more than 3.6 million scientific articles. At its core are Oreo, a high-throughput model for multimodal document parsing, and ColTrast, a query-aware encoder fine-tuning algorithm that enhances retrieval accuracy by using contrastive learning and late-interaction techniques. HiPerRAG delivers robust performance on existing scientific question answering (Q/A) benchmarks and two new benchmarks introduced in this work, achieving 90% accuracy on SciQ and 76% on PubMedQA—outperforming both domain-specific models like PubMedGPT and commercial LLMs such as GPT-4. Scaling to thousands of GPUs on the Polaris, Sunspot, and Frontier supercomputers, HiPerRAG delivers million document-scale RAG workflows for unifying scientific knowledge and fostering interdisciplinary innovation.

Authors

Institutions

Publication Details

Published
2025-06-16
DOI
https://doi.org/10.1145/3732775.3733586
Citations
6
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
14.89
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

Aswathy Ajith, Michael E. Papka, Francis J. Alexander, Anima Anandkumar et al.
6 citations
Topic Modeling
14.89
article

HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

Aswathy Ajith, Michael E. Papka, Francis J. Alexander, Anima Anandkumar, Ozan Gökdemir, Varuni Sastry, Arvind Ramanathan, Sam Foreman, Ian Foster, Nicholas Chia, Thomas Brettin, Rick Stevens, Huihuo Zheng, Alexander Brace, Tom Gibbs, Azton I. Wells, J. Gregory Pauloski, Venkatram Vishwanath, Kyle Hippe, Bharat Kale, Priyanka V. Setty, Carlo Siebenschuh, Heng Ma, Brian Hsu
article en
6 citations

Abstract

The volume of scientific literature is growing exponentially, leading to underutilized discoveries, duplicated efforts, and limited cross-disciplinary collaboration. Retrieval-Augmented Generation (RAG) offers a way to assist scientists by improving the factuality of Large Language Models (LLMs) in processing this influx of information. However, scaling RAG to handle millions of articles introduces significant challenges, including the high computational costs associated with parsing documents and embedding scientific knowledge, as well as the algorithmic complexity of aligning these representations with the nuanced semantics of scientific content. To address these issues, we introduce HiPerRAG, a RAG workflow powered by high performance computing (HPC) to index and retrieve knowledge from more than 3.6 million scientific articles. At its core are Oreo, a high-throughput model for multimodal document parsing, and ColTrast, a query-aware encoder fine-tuning algorithm that enhances retrieval accuracy by using contrastive learning and late-interaction techniques. HiPerRAG delivers robust performance on existing scientific question answering (Q/A) benchmarks and two new benchmarks introduced in this work, achieving 90% accuracy on SciQ and 76% on PubMedQA—outperforming both domain-specific models like PubMedGPT and commercial LLMs such as GPT-4. Scaling to thousands of GPUs on the Polaris, Sunspot, and Frontier supercomputers, HiPerRAG delivers million document-scale RAG workflows for unifying scientific knowledge and fostering interdisciplinary innovation.

California Institute of Technology (US), Argonne National Laboratory (US), University of Illinois Urbana-Champaign (US), University of Illinois Chicago (US), University of Chicago (US), Nvidia (United States) (US)
Openalex Percentile: Top 1%
Topic Modeling
14.89
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.