@inproceedings{javaji-etal-2025-ai,
    title = "Can {AI} Validate Science? Benchmarking {LLM}s on Claim {\textrightarrow}{E}vidence Reasoning in {AI} Papers",
    author = "Javaji, Shashidhar Reddy  and
      Cao, Yupeng  and
      Li, Haohang  and
      Yu, Yangyang  and
      Muralidhar, Nikhil  and
      Zhu, Zining",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-long.127/",
    pages = "2355--2379",
    ISBN = "979-8-89176-298-5"
}