Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
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.
Code (1)
Tasks
counterfactualIn-Context Learningtext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe robustness pitfall in deep learning models trained on single modal…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spu…
image-classificationImage Classificationzero-shot-classificationZero-Shot LearningConstructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort
Enhancing model interpretability can address spurious correlations by revealing how models draw their predictions. Concept Bottleneck Models (CBMs) can provide a principled way of disclosing and guiding model behaviors t…
Unsupervised Concept Discovery Mitigates Spurious Correlations
Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotati…
Representation LearningLabel-Efficient Group Robustness via Out-of-Distribution Concept Curation
Deep neural networks are prone to capture correlations between spurious attributes and class labels leading to low accuracy on some combinations of class labels and spurious attribute values. When a spurious attribut…
Attributeimage-classificationImage Classification