@inproceedings{kiepura-lam-2025-climatecheck2025,
    title = "{C}limate{C}heck2025: Multi-Stage Retrieval Meets {LLM}s for Automated Scientfic Fact-Checking",
    author = "Kiepura, Anna  and
      Lam, Jessica",
    editor = "Ghosal, Tirthankar  and
      Mayr, Philipp  and
      Singh, Amanpreet  and
      Naik, Aakanksha  and
      Rehm, Georg  and
      Freitag, Dayne  and
      Li, Dan  and
      Schimmler, Sonja  and
      De Waard, Anita",
    booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.sdp-1.28/",
    pages = "293--306",
    ISBN = "979-8-89176-265-7",
    abstract = "Misinformation on social media poses significant risks, particularly when it concerns critical scientific issues such as climate change. One promising direction for mitigation is the development of automated fact-checking systems that verify claims against authoritative scientific sources. In this work, we present our solution to the ClimateCheck2025 shared task, which involves retrieving and classifying scientific abstracts as evidence for or against given claims. Our system is built around a multi-stage hybrid retrieval pipeline that integrates lexical, sparse neural, and dense neural retrievers, followed by cross-encoder and large language model (LLM)-based reranking stages. For stance classification, we employ prompting strategies with LLMs to determine whether a retrieved abstract supports, refutes, or provides no evidence for a given claim. Our approach achieves the second-highest overall score across both subtasks of the benchmark and significantly surpasses the official baseline by 53.79{\%} on average across Recall@2, Recall@5, Recall@10, and B-Pref. Notably, we achieve state-of-the-art performance in Recall@2. These results highlight the effectiveness of combining structured retrieval architectures with the emergent reasoning capabilities of LLMs for scientific fact verification, especially in domains where reliable human annotation is scarce and timely intervention is essential."
}