@inproceedings{yadav-etal-2025-recall,
    title = "From Recall to Creation: Generating Follow-Up Questions Using Bloom{'}s Taxonomy and {G}rice{'}s Maxims",
    author = "Yadav, Archana  and
      Kashid, Harshvivek  and
      Sruthi, Medchalimi  and
      JayaPrakash, B  and
      Kullayappa, Chintalapalli Raja  and
      Reddy, Mandala Jagadeesh  and
      Bhattacharyya, Pushpak",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.acl-industry.93/",
    doi = "10.18653/v1/2025.acl-industry.93",
    pages = "1322--1338",
    ISBN = "979-8-89176-288-6",
    abstract = "In-car AI assistants enhance driving by enabling hands-free interactions, yet they often struggle with multi-turn conversations and fail to handle cognitively complex follow-up questions. This limits their effectiveness in real-world deployment. To address this limitation, we propose a framework that leverages Bloom{'}s Taxonomy to systematically generate follow-up questions with increasing cognitive complexity and a Gricean-inspired evaluation framework to assess their Logical Consistency, Informativeness, Relevance, and Clarity. We introduce a dataset comprising 750 human-annotated seed questions and 3750 follow-up questions, with human evaluation confirming that 96.68{\%} of the generated questions adhere to the intended Bloom{'}s Taxonomy levels. Our approach, validated through both LLM-based and human assessments, also identifies the specific cognitive complexity level at which in-car AI assistants begin to falter information that can help developers measure and optimize key cognitive aspects of conversational performance."
}