PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models

Xingwei He, A-Long Jin, Jun Ma, Yuan Yuan, Siu Yiu


Abstract
Factual Error Correction (FEC) aims to rectify false claims by making minimal revisions to align them more accurately with supporting evidence. However, the lack of datasets containing false claims and their corresponding corrections has impeded progress in this field. Existing distantly supervised models typically employ the mask-then-correct paradigm, where a masker identifies problematic spans in false claims, followed by a corrector to predict the masked portions. Unfortunately, accurately identifying errors in claims is challenging, leading to issues like over-erasure and incorrect masking. To overcome these challenges, we present PivotFEC, a method that enhances few-shot FEC with a pivot task approach using large language models (LLMs). Specifically, we introduce a pivot task called factual error injection, which leverages LLMs (e.g., ChatGPT) to intentionally generate text containing factual errors under few-shot settings; then, the generated text with factual errors can be used to train the FEC corrector. Our experiments on a public dataset demonstrate the effectiveness of PivotFEC in two significant ways: Firstly, it improves the widely-adopted SARI metrics by 11.3 compared to the best-performing distantly supervised methods. Secondly, it outperforms its few-shot counterpart (i.e., LLMs are directly used to solve FEC) by 7.9 points in SARI, validating the efficacy of our proposed pivot task.
Anthology ID:
2023.findings-emnlp.667
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9960–9976
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.667
DOI:
10.18653/v1/2023.findings-emnlp.667
Bibkey:
Cite (ACL):
Xingwei He, A-Long Jin, Jun Ma, Yuan Yuan, and Siu Yiu. 2023. PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9960–9976, Singapore. Association for Computational Linguistics.
Cite (Informal):
PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models (He et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.667.pdf