2024/07/23 by Pedro Ferreira, Ivan Titov, Ferreira, Pedro +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Seismology and Earthquake Studies
paper · doi:10.48550/arxiv.2407.16693
openalex publication_date 2024/07/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Explanation regularisation (ER) has been introduced as a way to guide text classifiers to form their predictions relying on input tokens that humans consider plausible. This is achieved by introducing an auxiliary explanation loss that measures how well the output of an input attribution technique for the model agrees with human-annotated rationales. The guidance appears to benefit performance in out-of-domain (OOD) settings, presumably due to an increased reliance on "plausible" tokens. However, previous work has under-explored the impact of guidance on that reliance, particularly when reliance is measured using attribution techniques different from those used to guide the model. In this work, we seek to close this gap, and also explore the relationship between reliance on plausible features and OOD performance. We find that the connection between ER and the ability of a classifier to rely on plausible features has been overstated and that a stronger reliance on plausible tokens does not seem to be the cause for OOD improvements.