e-FEVER: Explanations and Summaries forAutomated Fact Checking

Dominik Stammbach, Elliott Ash
2020 Conference for Truth and Trust Online  
This paper demonstrates the capability of a large pre-trained language model (GPT-3) to automatically generate explanations for fact checks. Given a claim and the retrieved potential evidence, our system summarizes the evidence and how it supports the fact-check determination. The system does not require any additional parameter training; instead, we use GPT-3's analogical "few-shot-learning" capability, where we provide a task description and some examples of solved tasks. We then subsequently
more » ... ask the model to explain new fact checks. Besides providing an intuitive and compressed summary for downstream users, we show that the machine-generated explanations can themselves serve as evidence for automatically making true/false determinations. Along the way, we report new competitive fact-checking results for the FEVER dataset. Finally, we make the explanations corpus publicly accessible, providing the first large-scale resource for explainable automated fact checking.
dblp:conf/tto/StammbachA20 fatcat:boqcmmymynai3oxzsnnudak56m