@inproceedings{carnerero-cano-etal-2026-factcorrector,
    title = "{F}act{C}orrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models",
    author = "Carnerero-Cano, Javier  and
      Pronesti, Massimiliano  and
      Marinescu, Radu  and
      Tchrakian, Tigran T.  and
      Barry, James  and
      Gajcin, Jasmina  and
      Hou, Yufang  and
      Pascale, Alessandra  and
      Daly, Elizabeth M.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2147/",
    pages = "46278--46307",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) are widely used in knowledge-intensive applications but often generate factually incorrect responses. A promising approach to rectify these flaws is correcting LLMs using feedback. Therefore, in this paper, we introduce FactCorrector, a new post-hoc correction method that adapts across domains without retraining and leverages structured feedback about the factuality of the original response to generate a correction. To support rigorous evaluations of factuality correction methods, we also develop the VELI5 benchmark, a novel dataset containing systematically injected factual errors and ground-truth corrections. Experiments on VELI5 and several popular long-form factuality datasets show that the FactCorrector approach significantly improves factual precision while preserving relevance, outperforming strong baselines. We release our code at https://ibm.biz/factcorrector."
}