EUVIMEDEUVIMED entdecken
Crossref

Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent Reasoning

Wuqiang Zheng, Yiyan Xu, Xinyu Lin, Chongming Gao, Wenjie Wang, Fuli Feng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 35041-35049

DOI: 10.1609/aaai.v40i41.40809 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wuqiang Zheng und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid and continuous increase in academic publications, identifying high-quality research has become an increasingly pressing challenge. While recent methods leveraging Large Language Models (LLMs) for automated paper evaluation have shown great promise, they are often constrained by outdated domain knowledge and limited reasoning capabilities. In this work, we present PaperEval, a novel LLM-based framework for automated paper evaluation that addresses these limitations through two key components: 1) a domain-aware paper retrieval module that retrieves relevant concurrent work to support contextualized assessments of novelty and contributions, and 2) a latent reasoning mechanism that enables deep understanding of complex motivations and methodologies, along with comprehensive comparison against concurrently related work, to support more accurate and reliable evaluation. To guide the reasoning process, we introduce a progressive ranking optimization strategy that encourages the LLM to iteratively refine its predictions with an emphasis on relative comparison. Experiments on two datasets demonstrate that PaperEval consistently outperforms existing methods in both academic impact and paper quality evaluation. In addition, we deploy PaperEval in a real-world paper recommendation system for filtering high-quality papers, which has gained strong engagement on social media---amassing over 8,000 subscribers and attracting over 10,000 views for many filtered high-quality papers---demonstrating the practical effectiveness of PaperEval.

Zitieren

APA

Zheng, W., Xu, Y., Lin, X., Gao, C., Wang, W., & Feng, F. (2026). Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 35041-35049. https://doi.org/10.1609/aaai.v40i41.40809

Vancouver

Zheng W, Xu Y, Lin X, Gao C, Wang W, Feng F. Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):35041-35049. doi:10.1609/aaai.v40i41.40809

BibTeX
@article{Zheng2026,
  author = {Zheng, Wuqiang and Xu, Yiyan and Lin, Xinyu and Gao, Chongming and Wang, Wenjie and Feng, Fuli},
  title = {Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent Reasoning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {41},
  pages = {35041--35049},
  doi = {10.1609/aaai.v40i41.40809}
}
Kostenlos starten →