ECLAIR: Enhanced Clarification for Interactive Responses

John Murzaku, Zifan Liu, Md. Mehrab Tanjim, Vaishnavi Muppala, Xiang Chen, Yunyao Li

AAAI 2025 pp. 28864-28870

doi:10.1609/AAAI.V39I28.35152 /aaai/2025/murzaku2025aaai-eclair-a/

Abstract

We present ECLAIR (Enhanced CLArification for Interactive Responses), a novel unified and end-to-end framework for interactive disambiguation in enterprise AI assistants. ECLAIR generates clarification questions for ambiguous user queries and resolves ambiguity based on the user's response. We introduce a generalized architecture capable of integrating ambiguity information from multiple downstream agents, enhancing context-awareness in resolving ambiguities and allowing enterprise specific definition of agents. We further define agents within our system that provide domain-specific grounding information. We conduct experiments comparing ECLAIR to few-shot prompting techniques and demonstrate ECLAIR's superior performance in clarification question generation and ambiguity resolution.

AAAI Semantic Scholar

Cite

Text

Murzaku et al. "ECLAIR: Enhanced Clarification for Interactive Responses." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35152

Markdown

[Murzaku et al. "ECLAIR: Enhanced Clarification for Interactive Responses." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/murzaku2025aaai-eclair-a/) doi:10.1609/AAAI.V39I28.35152

BibTeX

@inproceedings{murzaku2025aaai-eclair-a,
  title     = {{ECLAIR: Enhanced Clarification for Interactive Responses}},
  author    = {Murzaku, John and Liu, Zifan and Tanjim, Md. Mehrab and Muppala, Vaishnavi and Chen, Xiang and Li, Yunyao},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {28864-28870},
  doi       = {10.1609/AAAI.V39I28.35152},
  url       = {https://mlanthology.org/aaai/2025/murzaku2025aaai-eclair-a/}
}