ECLAIR: Enhanced Clarification for Interactive Responses
John Murzaku, Zifan Liu, Md Mehrab Tanjim, Vaishnavi Muppala, Xiang Chen, Yunyao Li
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.
BibTeX
@article{Murzaku_Liu_Tanjim_Muppala_Chen_Li_2025, title={ECLAIR: Enhanced Clarification for Interactive Responses}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35152}, DOI={10.1609/aaai.v39i28.35152}, abstractNote={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.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Murzaku, John and Liu, Zifan and Tanjim, Md Mehrab and Muppala, Vaishnavi and Chen, Xiang and Li, Yunyao}, year={2025}, month={Apr.}, pages={28864-28870} }