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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Murzaku, John, Liu, Zifan, Muppala, Vaishnavi, Tanjim, Md Mehrab, Chen, Xiang, Li, Yunyao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913760718880768
author Murzaku, John
Liu, Zifan
Muppala, Vaishnavi
Tanjim, Md Mehrab
Chen, Xiang
Li, Yunyao
author_facet Murzaku, John
Liu, Zifan
Muppala, Vaishnavi
Tanjim, Md Mehrab
Chen, Xiang
Li, Yunyao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
Murzaku, John
Liu, Zifan
Muppala, Vaishnavi
Tanjim, Md Mehrab
Chen, Xiang
Li, Yunyao
Computation and Language
68T50
I.2.7; H.5.2
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.
title ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant
topic Computation and Language
68T50
I.2.7; H.5.2
url https://arxiv.org/abs/2503.20791