Reinforcement Learning Guided Multi-Objective Exam Paper Generation

TL;DR

This paper introduces MOEPG, a reinforcement learning framework that optimizes multiple objectives for automatic exam paper generation, considering difficulty, score distribution, and skill coverage, using deep knowledge tracing and a novel question selection network.

Contribution

The paper presents a novel RL-based multi-objective exam paper generation framework that effectively balances multiple assessment criteria and models examinee skill levels.

Findings

MOEPG outperforms baseline methods in multiple evaluation metrics.

The framework effectively balances difficulty, score distribution, and skill coverage.

Experimental results validate the feasibility and effectiveness of MOEPG on real datasets.

Abstract

To reduce the repetitive and complex work of instructors, exam paper generation (EPG) technique has become a salient topic in the intelligent education field, which targets at generating high-quality exam paper automatically according to instructor-specified assessment criteria. The current advances utilize the ability of heuristic algorithms to optimize several well-known objective constraints, such as difficulty degree, number of questions, etc., for producing optimal solutions. However, in real scenarios, considering other equally relevant objectives (e.g., distribution of exam scores, skill coverage) is extremely important. Besides, how to develop an automatic multi-objective solution that finds an optimal subset of questions from a huge search space of large-sized question datasets and thus composes a high-quality exam paper is urgent but non-trivial. To this end, we skillfully design a reinforcement learning guided Multi-Objective Exam Paper Generation framework, termed MOEPG, to simultaneously optimize three exam domain-specific objectives including difficulty degree, distribution of exam scores, and skill coverage. Specifically, to accurately measure the skill proficiency of the examinee group, we first employ deep knowledge tracing to model the interaction information between examinees and response logs. We then design the flexible Exam Q-Network, a function approximator, which automatically selects the appropriate question to update the exam paper composition process. Later, MOEPG divides the decision space into multiple subspaces to better guide the updated direction of the exam paper. Through extensive experiments on two real-world datasets, we demonstrate that MOEPG is feasible in addressing the multiple dilemmas of exam paper generation scenario.