While large language models (LLMs) are increasingly integrated into learning environments as writing assistants or question-answering companions, their outputs often reflect hidden cultural biases and linguistic blind spots, raising risks of epistemic injustice (Fricker, 2007) and educational inequity if left unexamined (UNESCO, 2021; Ahmed et al., 2025). One underexplored factor is prompt design: the linguistic instructions shaping what knowledge an LLM retrieves, how it responds, and whose perspectives it centers (Cain, 2023). This paper addresses this gap by empirically comparing three prompt types: generic, role-based, and optimized empathy-guided prompts across 56 authentic learner questions from diverse higher education contexts. Using both reference-based metrics (METEOR: Banerjee & Lavie, 2005; BERTScore: Zhang et al., 2020) and a GPT-4 meta-evaluation framework for clarity, tone, and pedagogical appropriateness (Zhong et al., 2023), we show that prompts that frame the LLM as a supportive, context-aware respondent outperform generic instructions in producing answers rated as clearer, more encouraging, and more culturally attuned. Our findings align with relational pedagogy (Noddings, 2012) and Freirean critical pedagogy (Freire, 1970), highlighting how careful prompting can reduce algorithmic bias (Zhou et al., 2024) and support more equitable learning interactions. We argue that prompt design is not a neutral step but a pedagogical and ethical act with implications for developing community-driven, multilingual prompt libraries that embed fairness and respect for diverse learner voices into everyday AI use.

Authors:
Syed Hur Abbas, TU Dresden, Germany
Sandra Hummel, TU Dresden, Germany
Gitanjali Wadhwa, TU Dresden, Germany
Mana-Teresa Donner, TU Dresden, Germany

About the Presenter(s)
Syed Hur Abbas is a doctoral researcher at ScaDS.AI Dresden/Leipzig, working on LLM chatbots and AI mentoring for higher education. His expertise includes NLP, NLU, ML, and prompt engineering for fair, learner-centered AI.

Connect on Linkedin
https://www.linkedin.com/in/syed-hur-abbas/

See this presentation on the full schedule – Wednesday Schedule

Bookmark