Alert button
Picture for Tohid Ebrahim Ajdari

Tohid Ebrahim Ajdari

Alert button

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

Mar 06, 2023
Edoardo Mosca, Daryna Dementieva, Tohid Ebrahim Ajdari, Maximilian Kummeth, Kirill Gringauz, Georg Groh

Figure 1 for IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models
Figure 2 for IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models
Figure 3 for IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models
Figure 4 for 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 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 performance loss. 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/

* ACL Demo 2023 Submission 
Viaarxiv icon