Explore Spurious Correlations at the Concept Level in Language Models for Text Classification (2024.acl-long)
Copied to clipboard
| Challenge: | Language models have demonstrated remarkable performance in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. |
| Approach: | They propose a method to assess concept bias in models during fine-tuning and in-context learning using ChatGPT. |
| Outcome: | The proposed method outperforms token removal approaches and is validated through extensive testing. |
Similar Papers
Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing work identifies task-specific shortcuts via human priors or error analyses, which requires extensive expertise and efforts. |
| Approach: | They propose to automatically identify spurious correlations in NLP models at scale by using existing interpretability methods to extract tokens that significantly affect model’s decision process. |
| Outcome: | The proposed method can identify spurious correlations in NLP models at scale and mitigate these leads to more robust models in multiple applications. |
Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language (2022.naacl-main)
Copied to clipboard
| Challenge: | Spurious correlations are a threat to the trustworthiness of natural language processing systems. |
| Approach: | They propose a definition of spurious correlations in terms of conditional probabilities and a generalized definition of the term . they propose UIs that allow individual input features to be independent of labels. |
| Outcome: | The proposed definition can be generalized from uniformity to independence without affecting the claims of the paper. |
Analyzing Biases to Spurious Correlations in Text Classification Tasks (2022.aacl-short)
Copied to clipboard
| Challenge: | Often these systems exceed human performance, but there is a caveat: standard benchmarks often assume that training and evaluation data are drawn independently and identically from the same underlying distribution. |
| Approach: | They propose to exploit spurious correlations in training data to exploit these correlations . they show that even when only ‘stop’ words are available, it is possible to predict the class significantly better than random. |
| Outcome: | The proposed model can predict class significantly better when only ‘stop’ words are available at the input stage, but can degrade the ability of the system to generalize well to out-of-domain data. |
Stubborn Lexical Bias in Data and Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work has focused on spurious correlations between features and labels in training data . but, we find strong evidence of corresponding bias in the trained models . |
| Approach: | They propose a method to reduce spurious correlations in training data by reweighting it using a large pool of extracted features. |
| Outcome: | The proposed method reduces spurious correlations in training data, but still finds strong evidence of bias in trained models. |
Mitigating Shortcuts in Language Models with Soft Label Encoding (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. |
| Approach: | They propose a framework for debiasing shortcuts and a dummy class to encode shortcuts into a model and use it to generate soft labels. |
| Outcome: | The proposed framework significantly improves out-of-distribution generalization while maintaining satisfactory in-district accuracy. |
On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent work shows that deep learning models are sensitive to low-level correlations between simple features and specific output labels, leading to over-fitting and lack of generalization. |
| Approach: | They propose to eliminate single-word correlations altogether to mitigate this problem . they highlight several alternatives to dataset balancing to enhance contexts . |
| Outcome: | The proposed approach to balancing datasets is insufficient, the authors argue . they suggest enhancing datasets with richer contexts and abstaining from interaction . |
Identifying Spurious Correlations for Robust Text Classification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Text classifiers often rely on spurious correlations to predict positive reviews . term Spielberg does not cause the review to be positive, so it does not affect the classification accuracy. |
| Approach: | They propose a method to distinguish spurious and genuine correlations in text classification using treatment effect estimators. |
| Outcome: | The proposed method works well even with limited training examples and is possible to transport the word classifier to new domains. |
Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals (2023.acl-demo)
Copied to clipboard
| Challenge: | a spurious correlation exists when a feature correlates with the target label while there is no causal relationship between the feature and the label. |
| Approach: | They propose a dashboard that allows users to generate diverse and challenging examples by drawing inspiration from GPT-3 suggestions. |
| Outcome: | The proposed dashboard enables users to generate diverse and challenging examples by drawing inspiration from GPT-3 suggestions and make refinements based on the feedback. |
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models (2020.tacl-1)
Copied to clipboard
| Challenge: | Recent work shows that pre-trained language models perform poorly on challenging datasets where spurious correlations do not hold. |
| Approach: | They propose to use multi-task learning to improve generalization from minority examples . they propose to combine MTL with auxiliary tasks to improve performance . |
| Outcome: | The proposed model generalizes from minority examples without hurting in-distribution performance. |
Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens (2022.emnlp-main)
Copied to clipboard
| Challenge: | 'spurious correlations' have been used in NLP to informally denote any undesirable feature-label correlations. |
| Approach: | They formalize this distinction using a causal model and probabilities of necessity and sufficiency, which delineates causal relations between a feature and a label. |
| Outcome: | The proposed model is invariant to the feature, but not sufficient for prediction. |