@inproceedings{rashid-hakak-2025-fathom,
    title = "Fathom: A Fast and Modular {RAG} Pipeline for Fact-Checking",
    author = "Rashid, Farrukh Bin  and
      Hakak, Saqib",
    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-1.20/",
    doi = "10.18653/v1/2025.fever-1.20",
    pages = "258--265",
    ISBN = "978-1-959429-53-1",
    abstract = "We present Fathom, a Retrieval-Augmented Generation (RAG) pipeline for automated fact-checking, built entirely using lightweight open-source language models. The system begins with HyDE-style question generation to expand the context around each claim, followed by a dual-stage retrieval process using BM25 and semantic similarity to gather relevant evidence. Finally, a lightweight LLM performs veracity prediction, producing both a verdict and supporting rationale. Despite relying on smaller models, our system achieved an AVeriTeC score of 0.2043 on the test set, a 0.99{\%} absolute improvement over the baseline and 0.378 on the dev set, marking a 27.7{\%} absolute improvement."
}