MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization

TL;DR

This paper introduces MQAG, a novel information-theoretic framework for assessing summary quality by comparing source and summary answer distributions over automatically generated questions, outperforming existing methods.

Contribution

MQAG is a new approach that uses statistical distance between answer distributions to evaluate information consistency in summarization.

Findings

MQAG outperforms existing evaluation methods on multiple datasets.

Models trained on SQuAD or RACE achieve high accuracy in assessing summaries.

The approach effectively detects factual inconsistencies in summaries.

Abstract

State-of-the-art summarization systems can generate highly fluent summaries. These summaries, however, may contain factual inconsistencies and/or information not present in the source. Hence, an important component of assessing the quality of summaries is to determine whether there is information consistency between the source and the summary. Existing approaches are typically based on lexical matching or representation-based methods. In this work, we introduce an alternative scheme based on standard information-theoretic measures in which the information present in the source and summary is directly compared. We propose a Multiple-choice Question Answering and Generation framework, MQAG, which approximates the information consistency by computing the expected statistical distance between summary and source answer distributions over automatically generated multiple-choice questions. This approach exploits multiple-choice answer probabilities, as predicted answer distributions can be compared. We conduct experiments on four summary evaluation datasets: QAG-CNNDM/XSum, XSum-Hallucination, Podcast Assessment, and SummEval. Experiments show that MQAG, using models trained on SQuAD or RACE, outperforms existing evaluation methods on the majority of tasks.