Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

TL;DR

This paper investigates how language models rely on spurious concept-level correlations in text classification, using ChatGPT to identify concepts and generate counterfactual data to improve robustness against such biases.

Contribution

It introduces a novel approach employing ChatGPT for concept labeling and counterfactual data generation to detect and mitigate concept-level spurious correlations in language models.

Findings

ChatGPT effectively assigns concept labels to texts.

Counterfactual data reduces spurious correlations.

Method outperforms token removal approaches.

Abstract

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. Previous research has primarily concentrated on word, phrase, and syntax features, neglecting the concept level, often due to the absence of concept labels and difficulty in identifying conceptual content in input texts. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations. Our method's efficacy, surpassing traditional token removal approaches, is validated through extensive testing.