Incorporating User Feedback into Post-Training LLM Improvement to Promote Hermeneutical Justice
An interface to amplify marginalized voices
A. Turgut (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Anne Arzberger – Mentor (TU Delft - Web Information Systems)
Jie Yang – Mentor (TU Delft - Web Information Systems)
M.L. Tielman – Graduation committee member (TU Delft - Interactive Intelligence)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Generative AI can contribute to the misunderstanding or erasure of marginalized groups due to the insufficient nuanced data on their lived experiences. This limits the shared un- derstanding of their perspectives and contributes to a phenomenon called hermeneutical epistemic injustice. This study seeks to reduce this injustice by enabling real-life users from these groups to provide feedback that corrects the behavior of the model. However, victims of hermeneutical injustice struggle with articulating themselves, and current prac- tices lack sufficient support for user expression. Overcoming these challenges, we designed an interface to enable users to give feedback on the accuracy of the model, supported by a data processing workflow to ensure feasibility and scalability. We conducted a user study with 8 individuals with ADHD to evaluate whether the interface facilitates the extraction of accurate data, and found that it enables users to provide more concrete and precise feedback than existing methods, as it includes more guidance and control for the user.