Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search
This addresses the issue of unreliable summaries for users by reducing hallucinations, though it is an incremental improvement on existing methods.
The paper tackles the problem of hallucinations in abstractive summarization by introducing PINOCCHIO, a decoding method that constrains beam search to avoid unsupported statements, improving consistency by an average of ~67% on two datasets.
Abstractive summarization systems today produce fluent and relevant output, but often "hallucinate" statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that models hallucinate because they train on target summaries that are unsupported by the source. Based on our findings, we present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations. Given the model states and outputs at a given step, PINOCCHIO detects likely model hallucinations based on various measures of attribution to the source text. PINOCCHIO backtracks to find more consistent output, and can opt to produce no summary at all when no consistent generation can be found. In experiments, we find that PINOCCHIO improves the consistency of generation (in terms of F1) by an average of~67% on two abstractive summarization datasets.