PD$^3$: A Project Duplication Detection Framework via Adapted Multi-Agent Debate
This addresses project quality assessment for power experts by improving resource efficiency, though it is incremental as it builds on multi-agent debate methods.
The paper tackles project duplication detection by proposing PD³, a framework using adapted multi-agent debate, which outperforms existing methods by 7.43% and 8.00% in tasks and saves 5.73 million USD in initial detection costs.
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.