# RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question

Source: [RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question](<https://www.sota2.com/research/paper/68fa6f7e1e209131cea45f89>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:23:26.146Z

Authors: Alireza Mohammadshahi, Thomas Scialom, Majid Yazdani, Pouya Yanki, Angela Fan, James Henderson, Marzieh Saeidi

Published: 2022-11-02T21:10:09.000Z

## Abstract

Existing metrics for evaluating the quality of automatically generated questions such as BLEU, ROUGE, BERTScore, and BLEURT compare the reference and predicted questions, providing a high score when there is a considerable lexical overlap or semantic similarity between the candidate and the reference questions. This approach has two major shortcomings. First, we need expensive human-provided reference questions. Second, it penalises valid questions that may not have high lexical or semantic similarity to the reference questions. In this paper, we propose a new metric, RQUGE, based on the answerability of the candidate question given the context. The metric consists of a question-answering and a span scorer modules, using pre-trained models from existing literature, thus it can be used without any further training. We demonstrate that RQUGE has a higher correlation with human judgment without relying on the reference question. Additionally, RQUGE is shown to be more robust to several adversarial corruptions. Furthermore, we illustrate that we can significantly improve the performance of QA models on out-of-domain datasets by fine-tuning on synthetic data generated by a question generation model and re-ranked by RQUGE.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Paraphrase Evaluation on Quiz design dataset](<https://www.sota2.com/research/sota/paraphrase-evaluation-on-quiz-design-dataset.md>): Paraphrase Evaluation; Quiz design dataset; Pearson Correlation: 0.2932.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.01482>)

[PDF](<https://arxiv.org/pdf/2211.01482.pdf>)