MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification

TL;DR

MAPLE introduces a novel few-shot claim verification method that leverages micro language evolution analysis and unlabelled data to improve accuracy with minimal supervision, outperforming existing models.

Contribution

The paper presents MAPLE, a new approach using pairwise language evolution and a small seq2seq model for effective few-shot claim verification.

Findings

Significant performance improvements over SOTA baselines.

Effective use of unlabelled pairwise data.

Applicable across multiple fact-checking datasets.

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 here: https://github.com/XiaZeng0223/MAPLE