MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification
This addresses the problem of automated fact-checking with limited supervision, offering a resource-efficient solution for verifying claims against evidence.
The paper tackles few-shot claim verification by proposing MAPLE, a method that uses a small seq2seq model and a novel semantic measure to analyze alignment between claims and evidence, achieving significant performance improvements over SOTA baselines on datasets like FEVER, Climate FEVER, and SciFact.
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