@inproceedings{indrehus-etal-2025-semqa,
    title = "{S}em{QA}: Evaluating Evidence with Question Embeddings and Answer Entailment for Fact Verification",
    author = "Indrehus, Kjetil  and
      Vannebo, Caroline  and
      Pop, Roxana",
    editor = "Akhtar, Mubashara  and
      Aly, Rami  and
      Christodoulopoulos, Christos  and
      Cocarascu, Oana  and
      Guo, Zhijiang  and
      Mittal, Arpit  and
      Schlichtkrull, Michael  and
      Thorne, James  and
      Vlachos, Andreas",
    booktitle = "Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.fever-1.14/",
    doi = "10.18653/v1/2025.fever-1.14",
    pages = "184--200",
    ISBN = "978-1-959429-53-1",
    abstract = "Automated fact-checking (AFC) of factual claims require efficiency and accuracy. Existing evaluation frameworks like Ev$^2$R achieve strong semantic grounding but incur substantial computational cost, while simpler metrics based on overlap or one-to-one matching often misalign with human judgments. In this paper, we introduce SemQA, a lightweight and accurate evidence-scoring metric that combines transformer-based question scoring with bidirectional NLI entailment on answers. We evaluate SemQA by conducting human evaluations, analyzing correlations with existing metrics, and examining representative examples."
}