Generating Media Background Checks for Automated Source Critical Reasoning
This addresses the issue of misinformation for NLP systems and users by enabling automated source criticism, though it is incremental as it builds on existing retrieval-augmented models.
The paper tackles the problem of automated source credibility assessment in NLP by introducing a new task of generating media background checks, using a dataset of 6,709 checks derived from Media Bias / Fact Check, and finds that retrieval improves model performance and that these checks are helpful for both humans and models.
Not everything on the internet is true. This unfortunate fact requires both humans and models to perform complex reasoning about credibility when working with retrieved information. In NLP, this problem has seen little attention. Indeed, retrieval-augmented models are not typically expected to distrust retrieved documents. Human experts overcome the challenge by gathering signals about the context, reliability, and tendency of source documents - that is, they perform source criticism. We propose a novel NLP task focused on finding and summarising such signals. We introduce a new dataset of 6,709 "media background checks" derived from Media Bias / Fact Check, a volunteer-run website documenting media bias. We test open-source and closed-source LLM baselines with and without retrieval on this dataset, finding that retrieval greatly improves performance. We furthermore carry out human evaluation, demonstrating that 1) media background checks are helpful for humans, and 2) media background checks are helpful for retrieval-augmented models.