A Large Language Model-based Framework for Semi-Structured Tender Document Retrieval-Augmented Generation

TL;DR

This paper presents a framework that combines large language models with retrieval techniques to improve the accuracy and relevance of semi-structured procurement documents, addressing the lack of specialized knowledge in LLMs.

Contribution

The paper introduces a retrieval-augmented approach tailored for procurement document generation, enhancing LLM capabilities with domain-specific knowledge.

Findings

Improved accuracy in procurement document generation.

Enhanced relevance and compliance with legal standards.

Effective integration of retrieval techniques with LLMs.

Abstract

The drafting of documents in the procurement field has progressively become more complex and diverse, driven by the need to meet legal requirements, adapt to technological advancements, and address stakeholder demands. While large language models (LLMs) show potential in document generation, most LLMs lack specialized knowledge in procurement. To address this gap, we use retrieval-augmented techniques to achieve professional document generation, ensuring accuracy and relevance in procurement documentation.