Improved Beam Search for Hallucination Mitigation in Abstractive Summarization
This addresses hallucination in summarization for NLP applications, but it is incremental as it builds on existing beam search and NLI methods.
The paper tackled hallucination in abstractive summarization by proposing an NLI-assisted beam re-ranking mechanism during decoding, which significantly outperformed vanilla beam search on XSum and CNN/DM datasets.
Advancement in large pretrained language models has significantly improved their performance for conditional language generation tasks including summarization albeit with hallucinations. To reduce hallucinations, conventional methods proposed improving beam search or using a fact checker as a postprocessing step. In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation. We propose an NLI-assisted beam re-ranking mechanism by computing entailment probability scores between the input context and summarization model-generated beams during saliency-enhanced greedy decoding. Moreover, a diversity metric is introduced to compare its effectiveness against vanilla beam search. Our proposed algorithm significantly outperforms vanilla beam decoding on XSum and CNN/DM datasets.