# ECLAIR: Enhanced Clarification for Interactive Responses

arXiv: https://arxiv.org/abs/2503.15739 · HTML: https://mlsanity.com/paper/2503.15739/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 10 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 4 of 4)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance](https://mlsanity.com/paper/2210.08817/) (2022)

## Built on by (most cited first, 2 of 2)

- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [Not All Fallbacks Are Failures: Understanding and Recovering from Fallbacks in Mobile Voice Assistants](https://mlsanity.com/paper/2608.30738/) (2026)

## Abstract (arXiv)

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.