"I Don't Know What to Say": A Fact-Filling Questionnaire Method to Help Non-Experts Talk to LegalAI Assistant

Artificial intelligence has become increasingly prevalent in the legal domain. However, LegalAI systems often struggle with vague user queries that lack essential legal details, leading to suboptimal performance in practical applications. To address this challenge, we propose FactFiller, a novel approach that dynamically generates questionnaires to help users refine their input queries. Our method leverages an iterative training process that collects valuable questionnaires, eliminating the need for human annotation. Additionally, we introduce a "case-law-quiz" cascading retrieval process, ensuring that the generated questions and answer options are directly linked to specific legal provisions. Through the user study and the downstream task experiments, we demonstrate that FactFiller, while remaining easy for nonexperts to understand, not only improves the completeness of queries but also ensures the performance of various domain-specific models in downstream legal tasks. * Corresponding author User Query: I got injured at the construction site, and the company isn't helping me. What should I do? Court Document A) Unlabeled Training (Offline) Questioning Model Simulated User Fact Incomplete Query F il le d Q u e r y Remove Structured Questionnaire Court View Evaluator Auxiliary Model