@inproceedings{dai-etal-2026-r1,
    title = "R1-{RE}: Cross-Domain Relation Extraction with {RLVR}",
    author = "Dai, Runpeng  and
      Zheng, Tong  and
      Yang, Run  and
      Yu, Kaixian  and
      Zhu, Hongtu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1587/",
    pages = "34387--34401",
    ISBN = "979-8-89176-390-6",
    abstract = "Relation extraction (RE) is a core task in natural language processing. Traditional approaches typically frame RE as a supervised learning problem, directly mapping context to labels{---}an approach that often suffers from poor out-of-domain (OOD) generalization. Inspired by the workflow of human annotators, we reframe RE as a reasoning task guided by annotation guidelines and introduce R1-RE, the first reinforcement learning with verifiable reward (RLVR) framework for RE tasks. Our method elicits the reasoning abilities of small language models for annotation tasks, resulting in significantly improved OOD robustness. We evaluate our approach on the public Sem-2010 dataset and a private MDKG dataset. The R1-RE-7B model attains an average OOD accuracy of approximately 70{\%}, on par with leading proprietary models such as GPT-4o. Additionally, our comprehensive analysis provides novel insights into the training dynamics and emergent reasoning behaviors of the RLVR paradigm for RE."
}