Fact Checking Beyond Training Set

arXiv:2403.18671v1 Announce Type: cross
Abstract: Evaluating the veracity of everyday claims is time consuming and in some cases requires domain expertise. We empirically demonstrate that the commonly used fact checking pipeline, known as the retriever-reader, suffers from performance deterioration when it is trained on the labeled data from one domain and used in another domain. Afterwards, we delve into each component of the pipeline and propose novel algorithms to address this problem. We propose an adversarial algorithm to make the …

abstract arxiv beyond cases cs.cl cs.lg data domain expertise performance pipeline reader set training type