Papers › How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets

How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets

12 Jan 2022*SEM (NAACL) 2022 7arXiv:2201.04467archive 2025-07-28

Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis, Jörg Tiedemann

A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities. We present an extensive series of controlled experiments where pre-trained language models are exposed to data that have undergone specific corruption transformations. These involve removing instances of specific word classes and often lead to non-sensical sentences. Our results show that performance remains high on most GLUE tasks when the models are fine-tuned or tested on corrupted data, suggesting that they leverage other cues for prediction even in non-sensical contexts. Our proposed data transformations can be used to assess the extent to which a specific dataset constitutes a proper testbed for evaluating models' language understanding capabilities.

PaperPDFConference PDFCode

Code

helsinki-nlp/nlu-dataset-diagnostics officialmentioned in papermentioned on GitHubpytorch 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

Natural Language Understanding

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