MultiHint-9K: Orchestrating Human and AI Agency for Scalable Pedagogical Hint Generation
Proceedings of the Workshop on Orchestrating Human and AI Agency for Proactive and Reflective Learning (HAI-Agency 2026), co-located with the 27th International Conference on Artificial Intelligence in Education (AIED 2026), Seoul, Republic of Korea, CEUR Workshop Proceedings Vol-4248
Presented on
In short
The paper builds a pipeline in which human annotators set quality rubrics and AI agents generate, critique and refine Socratic hints, producing MultiHint-9K: 9,987 verified question-answer-hint tuples in English, Italian and Farsi. Fine-tuning five open models (7B to 24B) on the data improved ROUGE-L by about 67% over the base models, with the largest gains in Farsi.
Cite
@inproceedings{zeinalipour2026multihintk,
title = {MultiHint-9K: Orchestrating Human and AI Agency for Scalable Pedagogical Hint Generation},
author = {Kamyar Zeinalipour and Amir Sadeghi and Giovanni Angelini and Leonardo Rigutini and Marco Gori and Marco Maggini},
booktitle = {Proceedings of the Workshop on Orchestrating Human and AI Agency for Proactive and Reflective Learning (HAI-Agency 2026), co-located with AIED 2026},
year = {2026},
series = {CEUR Workshop Proceedings},
volume = {4248},
url = {https://ceur-ws.org/Vol-4248/short11.pdf}
}