# Can LLMs Ask Good Questions?

arXiv: https://arxiv.org/abs/2501.03491 · HTML: https://mlsanity.com/paper/2501.03491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 7 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [Generating Natural Questions About an Image](https://mlsanity.com/paper/1603.06059/) (2016)
- [HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution](https://mlsanity.com/paper/2307.16883/) (2023)
- [Recent Advances in Neural Question Generation](https://mlsanity.com/paper/1905.08949/) (2019)
- [Visual Question Generation as Dual Task of Visual Question Answering](https://mlsanity.com/paper/1709.07192/) (2017)
- [Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation](https://mlsanity.com/paper/2305.14327/) (2023)
- [Evaluating Open-QA Evaluation](https://mlsanity.com/paper/2305.12421/) (2023)
- [Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus](https://mlsanity.com/paper/1603.06807/) (2016)
- [AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL](https://mlsanity.com/paper/2208.12461/) (2022)
- [Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction](https://mlsanity.com/paper/2402.12170/) (2024)

## Abstract (arXiv)

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.