On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs
Nitay Calderon, Roi Reichart

TL;DR
This paper reviews recent trends in NLP model interpretability, emphasizing stakeholder perspectives, analyzing research across fields, and highlighting disparities between developers and users to guide future interpretability methods.
Contribution
It provides a comprehensive analysis of interpretability paradigms, stakeholder needs, and research trends in NLP, informed by large-scale paper analysis using LLMs.
Findings
Significant disparities between NLP developers and non-developer users.
Explanations of internal model components are rarely used outside NLP.
Research trends vary across different scientific fields.
Abstract
Recent advancements in NLP systems, particularly with the introduction of LLMs, have led to widespread adoption of these systems by a broad spectrum of users across various domains, impacting decision-making, the job market, society, and scientific research. This surge in usage has led to an explosion in NLP model interpretability and analysis research, accompanied by numerous technical surveys. Yet, these surveys often overlook the needs and perspectives of explanation stakeholders. In this paper, we address three fundamental questions: Why do we need interpretability, what are we interpreting, and how? By exploring these questions, we examine existing interpretability paradigms, their properties, and their relevance to different stakeholders. We further explore the practical implications of these paradigms by analyzing trends from the past decade across multiple research fields. To…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling
MethodsALIGN
