MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910310437224448 |
|---|---|
| author | Zeng, Xia Zubiaga, Arkaitz |
| author_facet | Zeng, Xia Zubiaga, Arkaitz |
| contents | 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 here: https://github.com/XiaZeng0223/MAPLE |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16282 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification Zeng, Xia Zubiaga, Arkaitz Computation and Language Artificial Intelligence Machine Learning 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 here: https://github.com/XiaZeng0223/MAPLE |
| title | MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.16282 |