Abstract
Claim verification is an essential step in the automated fact-checking pipeline which assesses the veracity of a claim against a piece of evidence. In this work, we explore the potential of few-shot claim verification, where only very limited data is available for supervision. We propose MAPLE (Micro Analysis of Pairwise Language Evolution), a pioneering approach that explores the alignment between a claim and its evidence with a small seq2seq model and a novel semantic measure. Its innovative utilization of micro language evolution path leverages unlabelled pairwise data to facilitate claim verification while imposing low demand on data annotations and computing resources. MAPLE demonstrates significant performance improvements over SOTA baselines SEED, PET and LLaMA 2 across three fact-checking datasets: FEVER, Climate FEVER, and SciFact. Data and code are available.- Anthology ID:
- 2024.findings-eacl.79
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2024
- Month:
- March
- Year:
- 2024
- Address:
- St. Julian’s, Malta
- Editors:
- Yvette Graham, Matthew Purver
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1177–1196
- Language:
- URL:
- https://aclanthology.org/2024.findings-eacl.79
- DOI:
- Cite (ACL):
- Xia Zeng and Arkaitz Zubiaga. 2024. MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1177–1196, St. Julian’s, Malta. Association for Computational Linguistics.
- Cite (Informal):
- MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification (Zeng & Zubiaga, Findings 2024)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2024.findings-eacl.79.pdf