Analyzing and Mitigating Negation Artifacts using Data Augmentation for Improving ELECTRA-Small Model Accuracy

Pre-trained models for natural language inference (NLI) often achieve high performance on benchmark datasets by using spurious correlations, or dataset artifacts, rather than understanding language touches such as negation. In this project, we investigate the performance of an ELECTRA-small model fine-tuned on the Stanford Natural Language Inference (SNLI) dataset, focusing on its handling of negation. Through analysis, we identify that the model struggles with correctly classifying examples containing negation. To address this, we augment the training data with contrast sets and adversarial examples emphasizing negation. Our results demonstrate that this targeted data augmentation improves the model's accuracy on negation-containing examples without adversely affecting overall performance, therefore mitigating the identified dataset artifact.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  2025-11-09

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.48550/arXiv.2511.06234arXiv 2511.06234
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Evaluating Models’ Local Decision Boundaries via Contrast Sets

  2020cited by this paper
• BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance

  2019cited by this paper
• Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference

  2019cited by this paper
• Adversarial NLI: A New Benchmark for Natural Language Understanding

  2019cited by this paper
• Stress Test Evaluation for Natural Language Inference

  2018cited by this paper
• Breaking NLI Systems with Sentences that Require Simple Lexical Inferences

  2018cited by this paper
• Hypothesis Only Baselines in Natural Language Inference

  2018cited by this paper
• Adversarial Examples for Evaluating Reading Comprehension Systems

  2017cited by this paper
• A large annotated corpus for learning natural language inference

  2015influential reference

• No citing papers are available for this paper.