# Follow-Up Questions Improve Documents Generated by Large Language Models

arXiv: https://arxiv.org/abs/2407.12017 · HTML: https://mlsanity.com/paper/2407.12017/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Template-Based Named Entity Recognition Using BART](https://mlsanity.com/paper/2106.01760/) (2021)
- [CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models](https://mlsanity.com/paper/2212.07769/) (2022)
- [CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models](https://mlsanity.com/paper/2405.12063/) (2024)
- [CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents](https://mlsanity.com/paper/2306.10376/) (2023)
- [An Empirical Study on the Usage of BERT Models for Code Completion](https://mlsanity.com/paper/2103.07115/) (2021)
- [What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys](https://mlsanity.com/paper/2205.10977/) (2022)

## Abstract (arXiv)

This study investigates the impact of Large Language Models (LLMs) generating follow-up questions in response to user requests for short (1-page) text documents. Users interacted with a novel web-based AI system designed to ask follow-up questions. Users requested documents they would like the AI to produce. The AI then generated follow-up questions to clarify the user's needs or offer additional insights before generating the requested documents. After answering the questions, users were shown a document generated using both the initial request and the questions and answers, and a document generated using only the initial request. Users indicated which document they preferred and gave feedback about their experience with the question-answering process. The findings of this study show clear benefits to question-asking both in document preference and in the qualitative user experience. This study further shows that users found more value in questions which were thought-provoking, open-ended, or offered unique insights into the user's request as opposed to simple information-gathering questions.