Adoption of Explainable Natural Language Processing: Perspectives from Industry and Academia on Practices and Challenges

2025-08-13

AI Summary

This paper addresses persistent real-world challenges hindering the adoption of interpretable NLP—namely, low practical uptake, methodological difficulties in evaluation, and poor user satisfaction. It presents the first systematic comparative study of practitioner perspectives across industry and academia. Through in-depth interviews and thematic analysis involving 42 engineers and researchers, the study identifies key drivers of adoption, prevailing technical preferences, salient usage barriers, and widespread dissatisfaction with current interpretability methods. Three core bottlenecks emerge: (1) a “concept–practice” gap between theoretical explanations and operational needs; (2) the absence of user-centered evaluation criteria; and (3) misalignment between existing tools and task-specific requirements. Based on these findings, the paper proposes a user-centered design framework and actionable definitions for interpretability, offering empirically grounded guidance for tool development, evaluation paradigms, and cross-disciplinary collaboration in interpretable NLP.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The field of explainable natural language processing (NLP) has grown rapidly in recent years. The growing opacity of complex models calls for transparency and explanations of their decisions, which is crucial to understand their reasoning and facilitate deployment, especially in high-stakes environments. Despite increasing attention given to explainable NLP, practitioners' perspectives regarding its practical adoption and effectiveness remain underexplored. This paper addresses this research gap by investigating practitioners' experiences with explainability methods, specifically focusing on their motivations for adopting such methods, the techniques employed, satisfaction levels, and the practical challenges encountered in real-world NLP applications. Through a qualitative interview-based study with industry practitioners and complementary interviews with academic researchers, we systematically analyze and compare their perspectives. Our findings reveal conceptual gaps, low satisfaction with current explainability methods, and highlight evaluation challenges. Our findings emphasize the need for clear definitions and user-centric frameworks for better adoption of explainable NLP in practice.

Problem

• Investigating motivations and challenges in adopting explainable NLP methods
• Comparing industry and academic perspectives on explainability techniques
• Addressing gaps in satisfaction and evaluation of current explainability methods

Innovation

• Qualitative interview-based study on explainable NLP
• Analyzing practitioner and academic perspectives systematically
• User-centric frameworks for explainable NLP adoption