IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models

Interpretability and human oversight are fundamental pillars of deploying complex NLP models into real-world applications. However, applying explainability and human-in-the-loop methods requires technical proficiency. Despite existing toolkits for model understanding and analysis, options to integra...

Full description

Saved in:

Bibliographic Details
Main Authors:	Mosca, Edoardo, Dementieva, Daryna, Ajdari, Tohid Ebrahim, Kummeth, Maximilian, Gringauz, Kirill, Zhou, Yutong, Groh, Georg
Format:	Journal Article
Language:	English
Published:	06-03-2023
Subjects:	Computer Science - Artificial Intelligence Computer Science - Computation and Language
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Interpretability and human oversight are fundamental pillars of deploying complex NLP models into real-world applications. However, applying explainability and human-in-the-loop methods requires technical proficiency. Despite existing toolkits for model understanding and analysis, options to integrate human feedback are still limited. We propose IFAN, a framework for real-time explanation-based interaction with NLP models. Through IFAN's interface, users can provide feedback to selected model explanations, which is then integrated through adapter layers to align the model with human rationale. We show the system to be effective in debiasing a hate speech classifier with minimal impact on performance. IFAN also offers a visual admin system and API to manage models (and datasets) as well as control access rights. A demo is live at https://ifan.ml.
DOI:	10.48550/arxiv.2303.03124