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.
Cite
@article{arxiv.2503.15739,
title = {ECLAIR: Enhanced Clarification for Interactive Responses},
author = {John Murzaku and Zifan Liu and Md Mehrab Tanjim and Vaishnavi Muppala and Xiang Chen and Yunyao Li},
journal= {arXiv preprint arXiv:2503.15739},
year = {2025}
}