PD$^3$: A Project Duplication Detection Framework via Adapted Multi-Agent Debate

TL;DR

PD$^3$ is a novel multi-agent debate framework for project duplication detection that outperforms existing methods and aids power experts in resource-efficient project review.

Contribution

It introduces a debate-based detection framework inspired by expert discussions, incorporating qualitative and quantitative feedback for improved accuracy.

Findings

Outperforms existing methods by 7.43% and 8.00% in two tasks.

Evaluated on over 800 real-world power projects across 20 fields.

Saved 5.73 million USD in initial project detection.

Abstract

Project duplication detection is critical for project quality assessment, as it improves resource utilization efficiency by preventing investing in newly proposed project that have already been studied. It requires the ability to understand high-level semantics and generate constructive and valuable feedback. Existing detection methods rely on basic word- or sentence-level comparison or solely apply large language models, lacking valuable insights for experts and in-depth comprehension of project content and review criteria. To tackle this issue, we propose PD$^3$, a Project Duplication Detection framework via adapted multi-agent Debate. Inspired by real-world expert debates, it employs a fair competition format to guide multi-agent debate to retrieve relevant projects. For feedback, it incorporates both qualitative and quantitative analysis to improve its practicality. Over 800 real-world power project data spanning more than 20 specialized fields are used to evaluate the framework, demonstrating that our method outperforms existing approaches by 7.43% and 8.00% in two downstream tasks. Furthermore, we establish an online platform, Review Dingdang, to assist power experts, saving 5.73 million USD in initial detection on more than 100 newly proposed projects.