AGenT Zero: Zero-shot Automatic Multiple-Choice Question Generation for Skill Assessments

TL;DR

AGenT Zero is a zero-shot, data-efficient method for generating multiple-choice questions for skill assessments using only pre-trained models, outperforming other methods in fluency and semantic similarity.

Contribution

It introduces a zero-shot MCQ generation pipeline that requires no fine-tuning and minimal data, emphasizing paraphrasing to reduce data acquisition costs.

Findings

Outperforms other pre-trained methods in fluency and semantic similarity

Requires no fine-tuning, only pre-trained models

Can be adapted to other question types like short answer or fill-in-the-blank

Abstract

Multiple-choice questions (MCQs) offer the most promising avenue for skill evaluation in the era of virtual education and job recruiting, where traditional performance-based alternatives such as projects and essays have become less viable, and grading resources are constrained. The automated generation of MCQs would allow assessment creation at scale. Recent advances in natural language processing have given rise to many complex question generation methods. However, the few methods that produce deployable results in specific domains require a large amount of domain-specific training data that can be very costly to acquire. Our work provides an initial foray into MCQ generation under high data-acquisition cost scenarios by strategically emphasizing paraphrasing the question context (compared to the task). In addition to maintaining semantic similarity between the question-answer pairs, our pipeline, which we call AGenT Zero, consists of only pre-trained models and requires no fine-tuning, minimizing data acquisition costs for question generation. AGenT Zero successfully outperforms other pre-trained methods in fluency and semantic similarity. Additionally, with some small changes, our assessment pipeline can be generalized to a broader question and answer space, including short answer or fill in the blank questions.