Conversational Text Extraction with Large Language Models Using Retrieval-Augmented Systems

TL;DR

This paper presents a retrieval-augmented system utilizing large language models to extract and summarize text from PDFs via a conversational interface, improving user interaction and information retrieval.

Contribution

The study introduces a novel retrieval-augmented approach combining LLMs and vector stores for effective PDF text extraction and summarization in a conversational setting.

Findings

Achieves competitive ROUGE scores for text extraction and summarization

Enables efficient, context-aware question answering from PDFs

Provides an intuitive interface for knowledge extraction from documents

Abstract

This study introduces a system leveraging Large Language Models (LLMs) to extract text and enhance user interaction with PDF documents via a conversational interface. Utilizing Retrieval-Augmented Generation (RAG), the system provides informative responses to user inquiries while highlighting relevant passages within the PDF. Upon user upload, the system processes the PDF, employing sentence embeddings to create a document-specific vector store. This vector store enables efficient retrieval of pertinent sections in response to user queries. The LLM then engages in a conversational exchange, using the retrieved information to extract text and generate comprehensive, contextually aware answers. While our approach demonstrates competitive ROUGE values compared to existing state-of-the-art techniques for text extraction and summarization, we acknowledge that further qualitative evaluation is necessary to fully assess its effectiveness in real-world applications. The proposed system gives competitive ROUGE values as compared to existing state-of-the-art techniques for text extraction and summarization, thus offering a valuable tool for researchers, students, and anyone seeking to efficiently extract knowledge and gain insights from documents through an intuitive question-answering interface.