ASE 2025
Sun 16 - Thu 20 November 2025 Seoul, South Korea

This program is tentative and subject to change.

Tue 18 Nov 2025 16:20 - 16:30 at Grand Hall 3 - Human and Social Aspects 2

Large Language Models (LLMs) have revolutionized the way natural language tasks are handled, with big potential applications in the context of education. LLMs can save educators time and effort, for instance, in content creation and exam generation. Although promising, LLMs’ integration into educational products brings some risks that companies must mitigate. In the context of an industrial project, we investigate the effectiveness of LLMs to generate educational multiple-choice questions. The experiments include 16 commercial and opensource LLMs, rely on standard metrics to assess the accuracy (F1 and BLEU) and linguistic quality (perplexity and diversity) of the generated questions, and compare with five specialized models. The results suggest that recent LLMs can outperform the fine-tuned models for question generation, open-source LLMs are very competitive with the commercial ones, with Meta Llama models being the best performing, and DeepSeek as performing as recent GPT4 models. This promising empirical evidence encourages us to focus on advanced prompting strategies, for which we report relevant open challenges we aim to address in the short term.

This program is tentative and subject to change.

Tue 18 Nov

Displayed time zone: Seoul change

16:00 - 16:50
Human and Social Aspects 2NIER Track / Industry Showcase at Grand Hall 3
16:00
10m
Talk
The Future of Software Transparency: Bridging Understanding, Measurement, and Practice
NIER Track
Gregorio Dalia University of Sannio, Annibale Panichella Delft University of Technology, Andrea Di Sorbo University of Sannio, Gerardo Canfora University of Sannio, Corrado A. Visaggio University of Sannio, Italy
16:10
10m
Talk
CodeACT-R: A Cognitive Simulation Framework for Human Attention in Code Reading
NIER Track
Yueke Zhang Vanderbilt University, Zihan Fang Vanderbilt University, Greg Trafton Naval Research Laboratory, Daniel Levin Vanderbilt University, Kevin Leach Vanderbilt University, Yu Huang Vanderbilt University
16:20
10m
Talk
Towards Reliable LLM-based Exam Generation. Lessons Learned and Open Challenges in an Industrial Project
Industry Showcase
Renzo Degiovanni Luxembourg Institute of Science and Technology, Jordi Cabot Luxembourg Institute of Science and Technology
16:30
10m
Talk
Tether: A Personalized Support Assistant for Software Engineers with ADHD
NIER Track
Aarsh Shah University of Calgary, Cleyton Magalhaes Universidade Federal Rural de Pernambuco, Kiev Gama Universidade Federal de Pernambuco, Ronnie de Souza Santos University of Calgary
16:40
10m
Talk
Autonomous Agents for Accessibility: Simulating Visual Impairments in Web Interfaces
NIER Track
Juan Diego Yepes-Parra Universidad de los Andes, Colombia, Camilo Escobar-Velásquez Universidad de los Andes, Colombia