Can LLMs Ask Good Questions?
This work provides insights into the distinctive characteristics of LLM-generated questions, informing future research on question quality and downstream applications, but it is incremental as it focuses on comparative analysis without introducing new methods.
The study evaluated questions generated by large language models (LLMs) from context, comparing them to human-authored questions across six dimensions, revealing that LLM-generated questions tend to demand longer descriptive answers and exhibit more evenly distributed context focus.
We evaluate questions generated by large language models (LLMs) from context, comparing them to human-authored questions across six dimensions: question type, question length, context coverage, answerability, uncommonness, and required answer length. Our study spans two open-source and two proprietary state-of-the-art models. Results reveal that LLM-generated questions tend to demand longer descriptive answers and exhibit more evenly distributed context focus, in contrast to the positional bias often seen in QA tasks. These findings provide insights into the distinctive characteristics of LLM-generated questions and inform future work on question quality and downstream applications.