@inproceedings{zhang-etal-2025-asktoact,
    title = "{A}sk{T}o{A}ct: Enhancing {LLM}s Tool Use via Self-Correcting Clarification",
    author = "Zhang, Xuan  and
      Shen, Yongliang  and
      Zheng, Zhe  and
      Wu, Linjuan  and
      Zhang, Wenqi  and
      Yan, Yuchen  and
      Peng, Qiuying  and
      Wang, Jun  and
      Lu, Weiming",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.682/",
    pages = "13495--13522",
    ISBN = "979-8-89176-332-6",
    abstract = "Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effective clarification. However, existing interactive clarification approaches face two critical limitations: reliance on manually constructed datasets, which inherently constrains training data scale and diversity, and lack of error correction mechanisms during multi-turn clarification, leading to error accumulation that compromises both accuracy and efficiency. We present AskToAct, which addresses these challenges by exploiting the structural mapping between queries and their tool invocation solutions. Our key insight is that tool parameters naturally represent explicit user intents. By systematically removing key parameters from queries while retaining them as ground truth, we enable automated construction of high-quality training data. We further enhance model robustness through error-correction pairs and selective masking, enabling dynamic error detection during clarification interactions. Comprehensive experiments demonstrate that AskToAct significantly outperforms existing approaches, achieving above 57{\%} accuracy in recovering critical unspecified intents and enhancing clarification efficiency by an average of 10.46{\%} while maintaining high accuracy in tool invocation. Our framework exhibits robust performance across different model architectures and successfully generalizes to entirely unseen APIs without additional training, achieving performance comparable to GPT-4o with substantially fewer computational resources."
}