@inproceedings{li-flanigan-2025-rac,
    title = "{RAC}: Efficient {LLM} Factuality Correction with Retrieval Augmentation",
    author = "Li, Changmao  and
      Flanigan, Jeffrey",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1370/",
    doi = "10.18653/v1/2025.findings-emnlp.1370",
    pages = "25145--25159",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective low-latency post-correction method, \textbf{Retrieval Augmented Correction (RAC)}, aimed at enhancing the factual performance of LLMs without requiring additional fine-tuning. Our method is general and can be used with any instruction-tuned LLM, and has greatly reduced latency compared to prior approaches. RAC decomposes the LLM{'}s output into atomic facts and applies a fine-grained verification and correction process with retrieved content to verify and correct the LLM-generated output. Our extensive experiments show that RAC yields up to 30{\%} improvements over the LLM baselines across three popular factuality evaluation datasets, validating its efficacy and robustness with and without the integration of Retrieval-Augmented Generation (RAG) across different LLMs. Notably, our method has reduced latency up to 40x and reduced token consumption up to 7x compared to previous state-of-the-art post-correction approaches with similar or better performance."
}