@inproceedings{zheng-etal-2026-isolated,
    title = "From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for {LLM}-Based Paper Evaluation",
    author = "Zheng, Pujun  and
      Yao, Jiacheng  and
      Zheng, Jinquan  and
      Gu, Chenyang  and
      He, Guoxiu  and
      Liu, Jiawei  and
      Huang, Yong  and
      Guo, Tianrui  and
      Lu, Wei",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1195/",
    pages = "23863--23883",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently. However, since score scales vary across conferences, time periods, and evaluation criteria, models trained on absolute scores are prone to fitting narrow, context-specific rules rather than developing robust scholarly judgment. To overcome this limitation, we propose shifting paper evaluation from isolated scoring to collaborative ranking. In particular, we design a $\textbf{C}$omparison-$\textbf{N}$ative framework for $\textbf{P}$aper $\textbf{E}$valuation ($\textbf{CNPE}$), integrating comparison into both data construction and model learning. We first propose a graph-based similarity ranking algorithm to facilitate the sampling of more informative and discriminative paper pairs from a collection. We then enhance relative quality judgment through supervised fine-tuning and reinforcement learning with comparison-based rewards. At inference, the model performs pairwise comparisons over sampled paper pairs and aggregates these preference signals into a global relative quality ranking. Experimental results demonstrate that our framework achieves an average relative improvement of $\textbf{21.8}${\%} over the strong baseline DeepReview-14B, while exhibiting robust generalization to five previously unseen datasets. Our code is available at https://github.com/ECNU-Text-Computing/ComparisonReview."
}