mFACE: Multilingual Summarization with Factual Consistency Evaluation

TL;DR

This paper introduces mFACE, a method that improves multilingual abstractive summarization by using factual consistency evaluation models to reduce hallucinations across 45 languages, enhancing summary accuracy.

Contribution

It proposes leveraging multilingual NLI models for data filtering and controlled generation to improve factual consistency in multilingual summarization.

Findings

Significant improvements over baselines in automatic metrics

Enhanced factual accuracy confirmed by human evaluation

Effective handling of 45 languages in the XLSum dataset

Abstract

Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries, reducing their utility for real-world application. Several recent efforts attempt to address this by devising models that automatically detect factual inconsistencies in machine generated summaries. However, they focus exclusively on English, a language with abundant resources. In this work, we leverage factual consistency evaluation models to improve multilingual summarization. We explore two intuitive approaches to mitigate hallucinations based on the signal provided by a multilingual NLI model, namely data filtering and controlled generation. Experimental results in the 45 languages from the XLSum dataset show gains over strong baselines in both automatic and human evaluation.