No file available
To read the file of this research,
you can request a copy directly from the authors.
Comparison of Large Language Models for Generating Contextually Relevant Questions
Preprints and early-stage research may not have been peer reviewed yet.
Abstract
This study explores the effectiveness of Large Language Models (LLMs) for Automatic Question Generation in educational settings. Three LLMs are compared in their ability to create questions from university slide text without fine-tuning. Questions were obtained in a two-step pipeline: first, answer phrases were extracted from slides using Llama 2-Chat 13B; then, the three models generated questions for each answer. To analyze whether the questions would be suitable in educational applications for students, a survey was conducted with 46 students who evaluated a total of 246 questions across five metrics: clarity, relevance, difficulty, slide relation, and question-answer alignment. Results indicate that GPT-3.5 and Llama 2-Chat 13B outperform Flan T5 XXL by a small margin, particularly in terms of clarity and question-answer alignment. GPT-3.5 especially excels at tailoring questions to match the input answers. The contribution of this research is the analysis of the capacity of LLMs for Automatic Question Generation in education.
ResearchGate has not been able to resolve any citations for this publication.
Controllable text generation (CTG) by large language models has a huge potential to transform education for teachers and students alike. Specifically, high quality and diverse question generation can dramatically reduce the load on teachers and improve the quality of their educational content. Recent work in this domain has made progress with generation, but fails to show that real teachers judge the generated questions as sufficiently useful for the classroom setting; or if instead the questions have errors and/or pedagogically unhelpful content. We conduct a human evaluation with teachers to assess the quality and usefulness of outputs from combining CTG and question taxonomies (Bloom's and a difficulty taxonomy). The results demonstrate that the questions generated are high quality and sufficiently useful, showing their promise for widespread use in the classroom setting.
Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience, and resources. This, in turn, hinders and slows down the use of educational activities (e.g. providing practice questions) and new advances (e.g. adaptive testing) that require a large pool of questions. To reduce the expenses associated with manual construction of questions and to satisfy the need for a continuous supply of new questions, automatic question generation (AQG) techniques were introduced. This review extends a previous review on AQG literature that has been published up to late 2014. It includes 93 papers that were between 2015 and early 2019 and tackle the automatic generation of questions for educational purposes. The aims of this review are to: provide an overview of the AQG community and its activities, summarise the current trends and advances in AQG, highlight the changes that the area has undergone in the recent years, and suggest areas for improvement and future opportunities for AQG. Similar to what was found previously, there is little focus in the current literature on generating questions of controlled difficulty, enriching question forms and structures, automating template construction, improving presentation, and generating feedback. Our findings also suggest the need to further improve experimental reporting, harmonise evaluation metrics, and investigate other evaluation methods that are more feasible.
Question generation aims to generate meaningful and fluent questions, which can address the lack of question-answer type annotated corpus by augmenting the available data. Using unannotated text with optional answers as input contents, question generation can be divided into two types based on whether answers are provided: answer-aware and answer-agnostic. While generating questions with providing answers is challenging, generating high-quality questions without providing answers is even more difficult, for both humans and machines. In order to address this issue, we proposed a novel end-to-end model called QGAE, which is able to transform answer-agnostic question generation into answer-aware question generation by directly extracting candidate answers. This approach effectively utilizes unlabeled data for generating high-quality question-answer pairs, and its end-to-end design makes it more convenient compared to a multi-stage method that requires at least two pre-trained models. Moreover, our model achieves better average scores and greater diversity. Our experiments show that QGAE achieves significant improvements in generating question-answer pairs, making it a promising approach for question generation.
Neural question generation (NQG) is the task of generating questions from the given context with deep neural networks. Previous answer-aware NQG methods suffer from the problem that the generated answers are focusing on entity and most of the questions are trivial to be answered. The answer-agnostic NQG methods reduce the bias towards named entities and increasing the model's degrees of freedom, but sometimes result in generating unanswerable questions which are not valuable for the subsequent machine reading comprehension system. In this paper, we treat the answers as the hidden pivot for question generation and combine the question generation and answer selection process in a joint model. We achieve the state-of-the-art result on the SQuAD dataset according to automatic metric and human evaluation.
This is a review of intervention studies in which students have been taught to generate questions as a means of improving their comprehension. Overall, teaching students the cognitive strategy of generating questions about the material they had read resulted in gains in comprehension, as measured by tests given at the end of the intervention. All tests were based on new material. The overall median effect size was 0.36 (64th percentile) when standardized tests were used and 0.86 (81st percentile) when experimenter-developed comprehension tests were used. The traditional skill-based instructional approach and the reciprocal teaching approach yielded similar results.
- T B Brown
Brown, T.B., et al.: Language Models are Few-Shot Learners (2020).
https://doi.org/10.48550/arXiv.2005.14165
Llama 2: Open Foundation and Fine-Tuned Chat Models
- H Touvron
Touvron, H., et al.: Llama 2: Open Foundation and Fine-Tuned Chat Models (2023).
https://doi.org/10.48550/arXiv.2307.09288
- A O Tzirides
Tzirides, A.O., et al.: Generative AI: Implications and Applications for Education
(2023). https://doi.org/10.48550/arXiv.2305.07605
Improving Question Generation with Multi-level Content Planning
- Z Xia
Xia, Z., et al.: Improving Question Generation with Multi-level Content Planning
(2023). https://doi.org/10.48550/arXiv.2310.13512