First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models

TL;DR

This paper introduces FATA, a new framework for AI dialogue that prompts large language models to generate supplementary questions before answering, improving response accuracy and user engagement through a single-turn, multi-domain approach.

Contribution

FATA is a novel interaction paradigm that emphasizes completeness and user participation, outperforming existing clarification methods with a single-turn, multi-domain design.

Findings

FATA improves response quality by approximately 40% over baseline prompts.

FATA demonstrates lower variability and higher stability compared to expert prompts.

Experimental results validate FATA's effectiveness across multiple domains.

Abstract

Large Language Models (LLMs) often struggle to deliver accurate and actionable answers when user-provided information is incomplete or ill-specified. We propose a new interaction paradigm, First Ask Then Answer (FATA), in which, through prompt words, LLMs are guided to proactively generate multidimensional supplementary questions for users prior to response generation. Subsequently, by integrating user-provided supplementary information with the original query through sophisticated prompting techniques, we achieve substantially improved response quality and relevance. In contrast to existing clarification approaches -- such as the CLAM framework oriented to ambiguity and the self-interrogation Self-Ask method -- FATA emphasizes completeness (beyond mere disambiguation) and user participation (inviting human input instead of relying solely on model-internal reasoning). It also adopts a single-turn strategy: all clarifying questions are produced at once, thereby reducing dialogue length and improving efficiency. Conceptually, FATA uses the reasoning power of LLMs to scaffold user expression, enabling non-expert users to formulate more comprehensive and contextually relevant queries. To evaluate FATA, we constructed a multi-domain benchmark and compared it with two controls: a baseline prompt (B-Prompt) and a context-enhanced expert prompt (C-Prompt). Experimental results show that FATA outperforms B-Prompt by approximately 40% in aggregate metrics and exhibits a coefficient of variation 8% lower than C-Prompt, indicating superior stability.