Skip to main navigation menu Skip to main content Skip to site footer

SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization


In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous  work has found that natural language inference (NLI) models do not perform competitively when applied to inconsistency detection. In this work, we revisit the use of NLI for inconsistency detection, finding that past work suffered from a mismatch in input granularity between NLI datasets (sentence-level), and  inconsistency detection (document level). We provide a highly effective and light-weight method called SummaCConv that enables NLI models to be successfully used for this task by segmenting documents into sentence units and aggregating scores between pairs of sentences. On our newly introduced benchmark called SummaC (Summary Consistency) consisting of six large inconsistency detection datasets, SummaCConv obtains state-of-the-art results with a balanced accuracy of 74.4%, a 5% point improvement compared to prior work.

Article at MIT Press Presented at ACL 2022