QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation
This addresses inconsistent evaluation in question generation for researchers and developers, though it is incremental as it builds on existing evaluation frameworks.
The paper tackles the lack of unified evaluation criteria in question generation by proposing QGEval, a benchmark that assesses generated questions and automatic metrics across 7 dimensions, finding that most models perform poorly in answerability and answer consistency, and existing metrics misalign with human judgments.
Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Through consistent evaluations of QG models and automatic metrics with QGEval, we find that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human judgments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and their evaluation.