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

2023/03/06 by Mosca, Edoardo, Dementieva, Daryna, Ajdari, Tohid Ebrahim +4 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2303.03124

Abstract

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.

Cited by

• Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection
• WATCHED: A Web AI Agent Tool for Combating Hate Speech by Expanding Data

Related

• Interactively Providing Explanations for Transformer Language Models
• InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations
• XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
• Improving Neural Model Performance through Natural Language Feedback on Their Explanations
• Explanation-Based Human Debugging of NLP Models: A Survey