Abstract

This paper introduces a novel problem of automated question generation for courtroom examinations, CourtQG. While question generation has been studied in domains such as educational testing and product description, CourtQG poses several unique challenges owing to its non-cooperative and agenda-driven nature. Specifically, not only the generated questions need to be relevant to the case and underlying context, they also have to achieve certain objectives such as challenging the opponent’s arguments and/or revealing potential inconsistencies in their answers. We propose to leverage large language models (LLM) for CourtQG by fine-tuning them on two auxiliary tasks, agenda explanation (ie, uncovering the underlying intents) and question type prediction. We additionally propose cold-start generation of questions from background documents without relying on examination history. We construct a dataset to evaluate our proposed method and show that it generates better questions according to standard metrics when compared to several baselines.

Metadata

publication

Proceedings of the 2024 Joint International Conference on Computational …, 2024

year

2024

publication date

2024/5

authors

Yi Fung, Anoop Kumar, Aram Galstyan, Heng Ji, Prem Natarajan

link

https://aclanthology.org/2024.lrec-main.49/

resource_link

https://aclanthology.org/2024.lrec-main.49.pdf

conference

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

pages

572-583