HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

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 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.

This paper has been accepted at the Platform for Advanced Scientific Computing Conference (PASC 25), June 16-18, 2025, Brugg-Windisch, Switzerland

References in corpus (9)

• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
• Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction
• Mistral 7B
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
• Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction
• BooookScore: A systematic exploration of book-length summarization in the era of LLMs
• Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications
• G-RAG: Knowledge Expansion in Material Science