Papers › On the Sensitivity and Stability of Model Interpretations in NLP

On the Sensitivity and Stability of Model Interpretations in NLP

18 Apr 2021ACL 2022 5arXiv:2104.08782archive 2025-07-28

Fan Yin, Zhouxing Shi, Cho-Jui Hsieh, Kai-Wei Chang

Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open problem how to define and quantitatively measure the faithfulness of interpretations, i.e., to what extent interpretations reflect the reasoning process by a model. We propose two new criteria, sensitivity and stability, that provide complementary notions of faithfulness to the existed removal-based criteria. Our results show that the conclusion for how faithful interpretations are could vary substantially based on different notions. Motivated by the desiderata of sensitivity and stability, we introduce a new class of interpretation methods that adopt techniques from adversarial robustness. Empirical results show that our proposed methods are effective under the new criteria and overcome limitations of gradient-based methods on removal-based criteria. Besides text classification, we also apply interpretation methods and metrics to dependency parsing. Our results shed light on understanding the diverse set of interpretations.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

uclanlp/nlp-interpretation-faithfulness officialmentioned in paperMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial RobustnessDependency ParsingSensitivityText Classificationtext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections