Towards Human-Like Educational Question Generation with Small Language Models

被引：1

作者：

Fawzi, Fares ^{[1
]}

Balan, Sarang ^{[1
]}

Cukurova, Mutlu ^{[1
]}

Yilmaz, Emine ^{[1
]}

Bulathwela, Sahan ^{[1
]}

机构：

[1] UCL, London, England

来源：

ARTIFICIAL INTELLIGENCE IN EDUCATION: POSTERS AND LATE BREAKING RESULTS, WORKSHOPS AND TUTORIALS, INDUSTRY AND INNOVATION TRACKS, PRACTITIONERS, DOCTORAL CONSORTIUM AND BLUE SKY, AIED 2024, PT I | 2024年 / 2150卷

关键词：

Question Generation; AI in Education; small Language Models;

D O I：

10.1007/978-3-031-64315-6_25

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

With the advent of Generative AI models, the automatic generation of educational questions plays a key role in developing online education. This work compares large-language model-based (LLM) systems and their small-language model (sLM) counterparts for educational question generation. Our experiments, quantitatively and qualitatively, demonstrate that sLMs can produce educational questions with comparable quality by further pre-training and fine-tuning.

引用

页码：295 / 303

页数：9

共 50 条

[21] Human-like problem-solving abilities in large language models using ChatGPT
Orru, Graziella
Piarulli, Andrea
Conversano, Ciro
Gemignani, Angelo
FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2023, 6
[22] Exploring Human-Like Attention Supervision in Visual Question Answering
Qiao, Tingting
Dong, Jianfeng
Xu, Duanqing
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 7300 - 7307
[23] Language and culture internalization for human-like autotelic AI
Cédric Colas
Tristan Karch
Clément Moulin-Frier
Pierre-Yves Oudeyer
Nature Machine Intelligence, 2022, 4 : 1068 - 1076
[24] Language and culture internalization for human-like autotelic AI
Colas, Cedric
Karch, Tristan
Moulin-Frier, Clement
Oudeyer, Pierre-Yves
NATURE MACHINE INTELLIGENCE, 2022, 4 (12) : 1068 - 1076
[25] Towards a Human-like Vision System for Driver Assistance
Fritsch, Jannik
Michalke, Thomas
Gepperth, Alexander
Bone, Sven
Waibel, Falko
Kleinehagenbrock, Marcus
Gayko, Jens
Goerick, Christian
2008 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3, 2008, : 612 - +
[26] Towards Industrial Robots with Human-like Moral Responsibilities
Curuklu, Baran
Dodig-Crnkovic, Gordana
Akan, Batu
PROCEEDINGS OF THE 5TH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI 2010), 2010, : 85 - 86
[27] Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles
Cui, Can
Ma, Yunsheng
Cao, Xu
Ye, Wenqian
Wang, Ziran
2024 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS, WACVW 2024, 2024, : 902 - 909
[28] Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT
Hagendorff, Thilo
Fabi, Sarah
Kosinski, Michal
NATURE COMPUTATIONAL SCIENCE, 2023, 3 (10): : 833 - +
[29] Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT
Thilo Hagendorff
Sarah Fabi
Michal Kosinski
Nature Computational Science, 2023, 3 : 833 - 838
[30] Generation of Human-Like Movements Based on Environmental Features
Zonta, A.
Smit, S. K.
Hoogendoorn, M.
Eiben, A. E.
2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 3079 - 3086

← 1 2 3 4 5 →