Saved in:
Bibliographic Details
Main Authors: Bao, Dezheng, Yang, Yueci, Chen, Xin, Jiang, Zhengxuan, Fei, Zeguo, Zhang, Daoze, Huang, Xuanwen, Chen, Junru, Yu, Chutian, Yuan, Xiang, Yang, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.17492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910964256866304
author Bao, Dezheng
Yang, Yueci
Chen, Xin
Jiang, Zhengxuan
Fei, Zeguo
Zhang, Daoze
Huang, Xuanwen
Chen, Junru
Yu, Chutian
Yuan, Xiang
Yang, Yang
author_facet Bao, Dezheng
Yang, Yueci
Chen, Xin
Jiang, Zhengxuan
Fei, Zeguo
Zhang, Daoze
Huang, Xuanwen
Chen, Junru
Yu, Chutian
Yuan, Xiang
Yang, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PD$^3$: A Project Duplication Detection Framework via Adapted Multi-Agent Debate
Bao, Dezheng
Yang, Yueci
Chen, Xin
Jiang, Zhengxuan
Fei, Zeguo
Zhang, Daoze
Huang, Xuanwen
Chen, Junru
Yu, Chutian
Yuan, Xiang
Yang, Yang
Artificial Intelligence
Computation and Language
Machine Learning
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.
title PD$^3$: A Project Duplication Detection Framework via Adapted Multi-Agent Debate
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.17492