Improving Factual Error Correction by Learning to Inject Factual Errors
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (16) · 18197-18205
DOI: 10.1609/aaai.v38i16.29778 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Xingwei He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Factual error correction (FEC) aims to revise factual errors in false claims with minimal editing, making them faithful to the provided evidence. This task is crucial for alleviating the hallucination problem encountered by large language models. Given the lack of paired data (i.e., false claims and their corresponding correct claims), existing methods typically adopt the ‘mask-then-correct’ paradigm. This paradigm relies solely on unpaired false claims and correct claims, thus being referred to as distantly supervised methods. These methods require a masker to explicitly identify factual errors within false claims before revising with a corrector. However, the absence of paired data to train the masker makes accurately pinpointing factual errors within claims challenging. To mitigate this, we propose to improve FEC by Learning to Inject Factual Errors (LIFE), a three-step distantly supervised method: ‘mask-corrupt-correct’. Specifically, we first train a corruptor using the ‘mask-then-corrupt’ procedure, allowing it to deliberately introduce factual errors into correct text. The corruptor is then applied to correct claims, generating a substantial amount of paired data. After that, we filter out low-quality data, and use the remaining data to train a corrector. Notably, our corrector does not require a masker, thus circumventing the bottleneck associated with explicit factual error identification. Our experiments on a public dataset verify the effectiveness of LIFE in two key aspects: Firstly, it outperforms the previous best-performing distantly supervised method by a notable margin of 10.59 points in SARI Final (19.3% improvement). Secondly, even compared to ChatGPT prompted with in-context examples, LIFE achieves a superiority of 7.16 points in SARI Final.
Zitieren
APA
He, X., Zhang, Q., Jin, A., Ma, J., Yuan, Y., & Yiu, S. M. (2024). Improving Factual Error Correction by Learning to Inject Factual Errors. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 18197-18205. https://doi.org/10.1609/aaai.v38i16.29778
Vancouver
He X, Zhang Q, Jin A, Ma J, Yuan Y, Yiu SM. Improving Factual Error Correction by Learning to Inject Factual Errors. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(16):18197-18205. doi:10.1609/aaai.v38i16.29778
BibTeX
@article{He2024,
author = {He, Xingwei and Zhang, Qianru and Jin, A-Long and Ma, Jun and Yuan, Yuan and Yiu, Siu Ming},
title = {Improving Factual Error Correction by Learning to Inject Factual Errors},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {16},
pages = {18197--18205},
doi = {10.1609/aaai.v38i16.29778}
}
EUVIMED