An official website of the United States government
Retrieval-augmented generation (RAG) services are rapidly gaining adoption in enterprise settings as they combine information retrieval systems (e.g., databases) with large language models (LLMs) to enhance response generation and reduce hallucinations. By augmenting an LLM’s fixed pre-trained knowledge with real-time information retrieval, RAG enables models to effectively extend their context to large knowledge bases by selectively retrieving only the most relevant information. As a result, RAG provides the effect of dynamic updates to the LLM’s knowledge without requiring expensive and time-consuming retraining. While some deployments keep the entire database in memory, RAG services are increasingly shifting toward persistent storage to accommodate ever-growing knowledge bases, enhance utility, and improve cost-efficiency. However, this transition fundamentally reshapes the system’s performance profile: empirical analysis reveals that the Search & Retrieval phase emerges as the dominant contributor to end-to-end latency. This phase typically involves (1) running a smaller language model to generate query embeddings, (2) executing similarity and relevance checks over varying data structures, and (3) performing frequent, long-latency accesses to persistent storage. To address this triad of challenges, we propose a metamorphic in-storage accelerator architecture that provides the necessary programmability to support diverse RAG algorithms, dynamic data structures, and varying computational patterns. The architecture also supports in-storage execution of smaller language models for query embedding generation while final LLM generation is executed on DGX A100 systems. Experimental results show up to 4.3 × and 1.5 × improvement in end-to-end throughput compared to conventional retrieval pipelines using Xeon CPUs with NVMe storage and A100 GPUs with DRAM, respectively.
more »
« less
This content will become publicly available on March 30, 2026
Accelerating Retrieval-Augmented Generation
An evolving solution to address hallucination and enhance accuracy in large language models (LLMs) is Retrieval-Augmented Generation (RAG), which involves augmenting LLMs with information retrieved from an external knowledge source, such as the web. This paper profiles several RAG execution pipelines and demystifies the complex interplay between their retrieval and generation phases. We demonstrate that while exact retrieval schemes are expensive, they can reduce inference time compared to approximate retrieval variants because an exact retrieval model can send a smaller but more accurate list of documents to the generative model while maintaining the same end-to-end accuracy. This observation motivates the acceleration of the exact nearest neighbor search for RAG. In this work, we design Intelligent Knowledge Store (IKS), a type-2 CXL device that implements a scale-out near-memory acceleration architecture with a novel cache-coherent interface between the host CPU and near-memory accelerators. IKS offers 13.4--27.9× faster exact nearest neighbor search over a 512GB vector database compared with executing the search on Intel Sapphire Rapids CPUs. This higher search performance translates to 1.7--26.3× lower end-to-end inference time for representative RAG applications. IKS is inherently a memory expander; its internal DRAM can be disaggregated and used for other applications running on the server to prevent DRAM -- which is the most expensive component in today's servers -- from being stranded.
more »
« less
- Award ID(s):
- 2402873
- PAR ID:
- 10618711
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400706981
- Page Range / eLocation ID:
- 15-32
- Format(s):
- Medium: X
- Location:
- Rotterdam, Netherlands
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Mills, Caitlin; Alexandron, Giora; Taibi, Davide; Lo_Bosco, Giosuè; Paquette, Luc (Ed.)Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that possess human-like ability in linguistic tasks are increasingly popular in assisting human graders to reduce their workload. However, LLMs' limitations in domain knowledge restrict their understanding in task-specific requirements and hinder their ability to achieve satisfactory performance. Retrieval-augmented generation (RAG) emerges as a promising solution by enabling LLMs to access relevant domain-specific knowledge during assessment. In this work, we propose an adaptive RAG framework for automated grading that dynamically retrieves and incorporates domain-specific knowledge based on the question and student answer context. Our approach combines semantic search and curated educational sources to retrieve valuable reference materials. Experimental results in a science education dataset demonstrate that our system achieves an improvement in grading accuracy compared to baseline LLM approaches. The findings suggest that RAG-enhanced grading systems can serve as reliable support with efficient performance gains.more » « less
-
As IoT device adoption grows, ensuring cybersecurity compliance with IoT standards, like National Institute of Standards and Technology Interagency (NISTIR) 8259A, has become increasingly complex. These standards are typically presented in lengthy, text-based formats that are difficult to process and query automatically. We built a knowledge graph to address this challenge to represent the key concepts, relationships, and references within NISTIR 8259A. We further integrate this knowledge graph with Retrieval-Augmented Generation (RAG) techniques that can be used by large language models (LLMs) to enhance the accuracy and contextual relevance of information retrieval. Additionally, we evaluate the performance of RAG using both graph-based queries and vector database embeddings. Our framework, implemented in Neo4j, was tested using multiple LLMs, including LLAMA2, Mistral-7B, and GPT-4. Our findings show that combining knowledge graphs with RAG significantly improves query precision and contextual relevance compared to unstructured vector-based retrieval methods. While traditional rule-based compliance tools were not evaluated in this study, our results demonstrate the advantages of structured, graph driven querying for security standards like NISTIR 8259A.more » « less
-
Approximate nearest neighbor search (ANNS) is a key retrieval technique for vector database and many data center applications, such as person re-identification and recommendation systems. It is also fundamental to retrieval augmented generation (RAG) for large language models (LLM) now. Among all the ANNS algorithms, graph-traversal-based ANNS achieves the highest recall rate. However, as the size of dataset increases, the graph may require hundreds of gigabytes of memory, exceeding the main memory capacity of a single workstation node. Although we can do partitioning and use solid-state drive (SSD) as the backing storage, the limited SSD I/O bandwidth severely degrades the performance of the system. To address this challenge, we present NDSEARCh, a hardware-software co-designed near-data processing (NDP) solution for ANNS processing. NDSeARCH consists of a novel in-storage computing architecture, namely, SEARSSD, that supports the ANNS kernels and leverages logic unit (LUN)-level parallelism inside the NAND flash chips. NDSEARCH also includes a processing model that is customized for NDP and cooperates with SearSSD. The processing model enables us to apply a two-level scheduling to improve the data locality and exploit the internal bandwidth in NDSearch, and a speculative searching mechanism to further accelerate the ANNS workload. Our results show that NDSEARCH improves the throughput by up to 31.7×,14.6×,7.4×, and 2.9× over CPU, GPU, a state-of-the-art SmartSSD-only design, and DeepStore, respectively. NDSEARCH also achieves two orders-of-magnitude higher energy efficiency than CPU and GPU.more » « less
-
Large Language Models (LLMs) are pre-trained on large-scale corpora and excel in numerous general natural language processing (NLP) tasks, such as question answering (QA). Despite their advanced language capabilities, when it comes to domain-specific and knowledge-intensive tasks, LLMs suffer from hallucinations, knowledge cut-offs, and lack of knowledge attributions. Additionally, fine tuning LLMs' intrinsic knowledge to highly specific domains is an expensive and time consuming process. The retrieval-augmented generation (RAG) process has recently emerged as a method capable of optimization of LLM responses, by referencing them to a predetermined ontology. It was shown that using a Knowledge Graph (KG) ontology for RAG improves the QA accuracy, by taking into account relevant sub-graphs that preserve the information in a structured manner. In this paper, we introduce SMART-SLIC, a highly domain-specific LLM framework, that integrates RAG with KG and a vector store (VS) that store factual domain specific information. Importantly, to avoid hallucinations in the KG, we build these highly domain-specific KGs and VSs without the use of LLMs, but via NLP, data mining, and nonnegative tensor factorization with automatic model selection. Pairing our RAG with a domain-specific: (i) KG (containing structured information), and (ii) VS (containing unstructured information) enables the development of domain-specific chat-bots that attribute the source of information, mitigate hallucinations, lessen the need for fine-tuning, and excel in highly domain-specific question answering tasks. We pair SMART-SLIC with chain-of-thought prompting agents. The framework is designed to be generalizable to adapt to any specific or specialized domain. In this paper, we demonstrate the question answering capabilities of our framework on a corpus of scientific publications on malware analysis and anomaly detection.more » « less
