Streamlining Industrial Contract Management with Retrieval-Augmented LLMs
This addresses the problem of inefficient contract revision workflows for industrial partners, though it is incremental as it builds on existing RAG methods.
The paper tackled automating contract management by developing a retrieval-augmented generation framework to identify and optimize problematic contract revisions, achieving over 80% accuracy in both tasks under real-world, low-resource conditions.
Contract management involves reviewing and negotiating provisions, individual clauses that define rights, obligations, and terms of agreement. During this process, revisions to provisions are proposed and iteratively refined, some of which may be problematic or unacceptable. Automating this workflow is challenging due to the scarcity of labeled data and the abundance of unstructured legacy contracts. In this paper, we present a modular framework designed to streamline contract management through a retrieval-augmented generation (RAG) pipeline. Our system integrates synthetic data generation, semantic clause retrieval, acceptability classification, and reward-based alignment to flag problematic revisions and generate improved alternatives. Developed and evaluated in collaboration with an industry partner, our system achieves over 80% accuracy in both identifying and optimizing problematic revisions, demonstrating strong performance under real-world, low-resource conditions and offering a practical means of accelerating contract revision workflows.