ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant

Abstract

Large language models (LLMs) have shown remarkable progress in understanding and generating natural language across various applications. However, they often struggle with resolving ambiguities in real-world, enterprise-level interactions, where context and domain-specific knowledge play a crucial role. In this demonstration, we introduce ECLAIR (Enhanced CLArification for Interactive Responses), a multi-agent framework for interactive disambiguation. ECLAIR enhances ambiguous user query clarification through an interactive process where custom agents are defined, ambiguity reasoning is conducted by the agents, clarification questions are generated, and user feedback is leveraged to refine the final response. When tested on real-world customer data, ECLAIR demonstrates significant improvements in clarification question generation compared to standard few-shot methods.

Cite

Text

Murzaku et al. "ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35363

Markdown

[Murzaku et al. "ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/murzaku2025aaai-eclair/) doi:10.1609/AAAI.V39I28.35363

BibTeX

@inproceedings{murzaku2025aaai-eclair,
  title     = {{ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant}},
  author    = {Murzaku, John and Liu, Zifan and Muppala, Vaishnavi and Tanjim, Md. Mehrab and Chen, Xiang and Li, Yunyao},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {29673-29675},
  doi       = {10.1609/AAAI.V39I28.35363},
  url       = {https://mlanthology.org/aaai/2025/murzaku2025aaai-eclair/}
}