This paper investigates the enhancement of scientific literature chatbots through retrieval-augmented generation (RAG), with a focus on evaluating vector- and graph-based retrieval systems. The proposed chatbot leverages both structured (graph) and unstructured (vector) databases to access scientific articles and gray literature, enabling efficient triage of sources according to research objectives. To systematically assess performance, we examine two use-case scenarios: retrieval from a single uploaded document and retrieval from a large-scale corpus. Benchmark test sets were generated using a GPT model, with selected outputs annotated for evaluation. The comparative analysis emphasizes retrieval accuracy and response relevance, providing insight into the strengths and limitations of each approach. The findings demonstrate the potential of hybrid RAG systems to improve accessibility to scientific knowledge and to support evidence-based decision making.
Comparing the Utility, Preference, and Performance of Course Material Search Functionality and Retrieval-Augmented Generation Large Language Model (RAG-LLM) AI Chatbots in Information-Seeking Tasks
Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation
School of Computing Newcastle University（计算学院新castle大学）
A Multimodal Manufacturing Safety Chatbot: Knowledge Base Design, Benchmark Development, and Evaluation of Multiple RAG Approaches
Farmer School of Business, Miami University（Miami大学农业商学院）；Department of Computer Science and Software Engineering, Miami University（Miami大学计算机科学与软件工程系）；Department of Engineering Technology, Miami University（Miami大学工程技术系）；Department of Mechanical and Manufacturing Engineering, Miami University（Miami大学机械与制造工程系）；Department of Industrial and Systems Engineering, University at Buffalo（University at Buffalo工业与系统工程系）
HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
Argonne National Laboratory（阿贡国家实验室）；The University of Chicago（芝加哥大学）；NVIDIA Inc.（NVIDIA公司）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；California Institute of Technology（加州理工学院）
MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation
Istituto di Informatica e Telematica, Consiglio Nazionale Delle Ricerche（国家研究委员会信息与自动化研究所）；TeCIP, Scuola Universitaria Superiore Sant’Anna（圣安娜高等学校TeCIP研究所）；University of Padua（帕多瓦大学）；Delft University of Technology（代尔夫特理工大学）
OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；Meta；University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）；Stanford University（斯坦福大学）
SpectraQuery: A Hybrid Retrieval-Augmented Conversational Assistant for Battery Science
Mechanical Engineering, Stanford University（斯坦福大学机械工程系）；Applied Energy Division, SLAC National Accelerator Laboratory（SLAC国家加速器实验室应用能源部门）；Institute of Computational and Mathematical Engineering, Stanford University（斯坦福大学计算与数学工程研究所）
