# Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causality

arXiv: https://arxiv.org/abs/2310.07588 · HTML: https://mlsanity.com/paper/2310.07588/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 58 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [A Survey on Causal Inference](https://mlsanity.com/paper/2002.02770/) (2020)
- [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://mlsanity.com/paper/2005.13407/) (2020)
- [Causal Attention for Vision-Language Tasks](https://mlsanity.com/paper/2103.03493/) (2021)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals](https://mlsanity.com/paper/2012.10040/) (2020)
- [Deconfounded Recommendation for Alleviating Bias Amplification](https://mlsanity.com/paper/2105.10648/) (2021)
- [Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue](https://mlsanity.com/paper/2009.09945/) (2020)
- [Retrieval-guided Counterfactual Generation for QA](https://mlsanity.com/paper/2110.07596/) (2021)
- [Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning](https://mlsanity.com/paper/2106.03103/) (2021)
- [Order-free Learning Alleviating Exposure Bias in Multi-label Classification](https://mlsanity.com/paper/1909.03434/) (2019)
- [Sufficient Dimension Reduction for Average Causal Effect Estimation](https://mlsanity.com/paper/2009.06444/) (2020)
- [Multi-relation Message Passing for Multi-label Text Classification](https://mlsanity.com/paper/2202.04844/) (2022)

## Built on by (most cited first, 1 of 1)

- [Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding](https://mlsanity.com/paper/2310.11721/) (2023)

## Abstract (arXiv)

Multi-Label Text Classification (MLTC) aims to assign the most relevant labels to each given text. Existing methods demonstrate that label dependency can help to improve the model's performance. However, the introduction of label dependency may cause the model to suffer from unwanted prediction bias. In this study, we attribute the bias to the model's misuse of label dependency, i.e., the model tends to utilize the correlation shortcut in label dependency rather than fusing text information and label dependency for prediction. Motivated by causal inference, we propose a CounterFactual Text Classifier (CFTC) to eliminate the correlation bias, and make causality-based predictions. Specifically, our CFTC first adopts the predict-then-modify backbone to extract precise label information embedded in label dependency, then blocks the correlation shortcut through the counterfactual de-bias technique with the help of the human causal graph. Experimental results on three datasets demonstrate that our CFTC significantly outperforms the baselines and effectively eliminates the correlation bias in datasets.