ClimateCheck2025: Multi-Stage Retrieval Meets LLMs for Automated Scientfic Fact-Checking

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 1 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 final baseline by 53.76% on Subtask I score (defined as an average across Recall@2, Recall@5, Recall@10, and B-Pref).Notably, we achieve state-of-theart performance in [email protected] 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.