A Quick, trustworthy spectral knowledge Q&A system leveraging retrieval-augmented generation on LLM

2024-08-21

AI Summary

To address low retrieval efficiency, high redundancy, and poor traceability in spectral analysis knowledge discovery, this paper proposes a trustworthy question-answering system tailored to the domain. Methodologically: (1) we release SDAAP—the first open-source textual knowledge dataset specifically for spectral analysis; (2) we introduce a knowledge-traceable Retrieval-Augmented Generation (RAG) framework that constrains large language models (LLMs) to general-purpose generation while enabling precise, anchor-based retrieval through joint entity recognition and a domain-specific knowledge graph; (3) we enhance domain expertise via fine-tuning and prompt engineering. Experimental results demonstrate that our system significantly outperforms baseline models in answer accuracy, domain specificity, and source traceability: every generated answer is precisely grounded in original literature passages, thereby enabling efficient and reliable scientific knowledge acquisition.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Community question answering
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Large Language Model (LLM) has demonstrated significant success in a range of natural language processing (NLP) tasks within general domain. The emergence of LLM has introduced innovative methodologies across diverse fields, including the natural sciences. Researchers aim to implement automated, concurrent process driven by LLM to supplant conventional manual, repetitive and labor-intensive work. In the domain of spectral analysis and detection, it is imperative for researchers to autonomously acquire pertinent knowledge across various research objects, which encompasses the spectroscopic techniques and the chemometric methods that are employed in experiments and analysis. Paradoxically, despite the recognition of spectroscopic detection as an effective analytical method, the fundamental process of knowledge retrieval remains both time-intensive and repetitive. In response to this challenge, we first introduced the Spectral Detection and Analysis Based Paper(SDAAP) dataset, which is the first open-source textual knowledge dataset for spectral analysis and detection and contains annotated literature data as well as corresponding knowledge instruction data. Subsequently, we also designed an automated Q&A framework based on the SDAAP dataset, which can retrieve relevant knowledge and generate high-quality responses by extracting entities in the input as retrieval parameters. It is worth noting that: within this framework, LLM is only used as a tool to provide generalizability, while RAG technique is used to accurately capture the source of the knowledge.This approach not only improves the quality of the generated responses, but also ensures the traceability of the knowledge. Experimental results show that our framework generates responses with more reliable expertise compared to the baseline.

Problem

• Automating spectral knowledge retrieval to replace manual work
• Creating first open-source dataset for spectral analysis
• Improving response reliability in spectral knowledge Q&A

Innovation

• Introduces SDAAP dataset for spectral analysis
• Uses RAG technique for accurate knowledge retrieval
• LLM enhances response generalizability and reliability