@inproceedings{mazzaccara-etal-2024-learning,
    title = "Learning to Ask Informative Questions: Enhancing {LLM}s with Preference Optimization and Expected Information Gain",
    author = "Mazzaccara, Davide  and
      Testoni, Alberto  and
      Bernardi, Raffaella",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.291/",
    doi = "10.18653/v1/2024.findings-emnlp.291",
    pages = "5064--5074",
    abstract = "Questions are essential tools for acquiring the necessary information to complete information-seeking tasks. However, large language models (LLMs), especially open-source models, often perform poorly in generating informative questions, as measured by expected information gain (EIG). In this paper, we propose a method to enhance the informativeness of LLM-generated questions in 20-question game dialogues. We sample multiple questions from the same model (LLaMA 2-Chat 7B) for each game and create pairs of low-EIG and high-EIG questions to apply a Direct Preference Optimization (DPO) algorithm. Our results show that this method produces more effective questions (in terms of EIG), even in domains different from those used to train the DPO model."
}