Incorporating Respect into LLM-Based Academic Feedback: A BI-R Framework for Instructing Students after Q&A Sessions

Mayuko Aiba, Daisuke Saito, Nobuaki Minematsu


Abstract
In academic research, post-presentation Q&A sessions are crucial for deepening understanding and shaping research directions. Supervisors’ comments are particularly valuable when they highlight perspectives that students have not yet fully considered. Such comments typically arise from careful reasoning within dialogue, yet large language models (LLMs) still struggle to reason precisely about dialogue context and communicative intentions. Building on LLMs, this study proposes a feedback generation framework based on the Belief–Desire–Intention (BDI) model, which conceptualizes Q&A sessions as cognitive interactions between presenters and questioners. We further extend this framework into BI-R by introducing Respect as an explicit dimension, ensuring that generated feedback is not only accurate but also pedagogically constructive. We evaluated the proposed framework (BDI and BI-R) through comparative experiments with master’s students and field experiments with doctoral students during pre-defense presentations. Results showed that while the BDI prompt did not outperform the baseline, the BI-R prompt was particularly effective when students did not fully grasp the broader context or background of the questions. When comparing BDI and BI-R, the inclusion of Respect improved the tone and pedagogical appropriateness of feedback. These findings highlight the potential of the proposed framework as a supportive tool for training students and early-career researchers.
Anthology ID:
2026.iwsds-1.29
Volume:
Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
Month:
February
Year:
2026
Address:
Trento, Italy
Editors:
Giuseppe Riccardi, Seyed Mahed Mousavi, Maria Ines Torres, Koichiro Yoshino, Zoraida Callejas, Shammur Absar Chowdhury, Yun-Nung Chen, Frederic Bechet, Joakim Gustafson, Géraldine Damnati, Alex Papangelis, Luis Fernando D’Haro, John Mendonça, Raffaella Bernardi, Dilek Hakkani-Tur, Giuseppe "Pino" Di Fabbrizio, Tatsuya Kawahara, Firoj Alam, Gokhan Tur, Michael Johnston
Venue:
IWSDS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
288–301
Language:
URL:
https://aclanthology.org/2026.iwsds-1.29/
DOI:
Bibkey:
Cite (ACL):
Mayuko Aiba, Daisuke Saito, and Nobuaki Minematsu. 2026. Incorporating Respect into LLM-Based Academic Feedback: A BI-R Framework for Instructing Students after Q&A Sessions. In Proceedings of the 16th International Workshop on Spoken Dialogue System Technology, pages 288–301, Trento, Italy. Association for Computational Linguistics.
Cite (Informal):
Incorporating Respect into LLM-Based Academic Feedback: A BI-R Framework for Instructing Students after Q&A Sessions (Aiba et al., IWSDS 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwsds-1.29.pdf