ECLAIR: Enhanced Clarification for Interactive Responses
By: John Murzaku , Zifan Liu , Md Mehrab Tanjim and more
Potential Business Impact:
Helps AI assistants understand confusing questions better.
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.
Similar Papers
ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
Computation and Language
Helps computers understand confusing questions better.
Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
Human-Computer Interaction
Helps robots understand what you mean and point at.
Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue
Robotics
Robot asks questions to do tasks better.