Papers › Counterfactual Inference for Text Classification Debiasing

Counterfactual Inference for Text Classification Debiasing

1 Aug 2021ACL 2021 5archive 2025-07-28

Chen Qian, Fuli Feng, Lijie Wen, Chunping Ma, Pengjun Xie

Today{'}s text classifiers inevitably suffer from unintended dataset biases, especially the document-level label bias and word-level keyword bias, which may hurt models{'} generalization. Many previous studies employed data-level manipulations or model-level balancing mechanisms to recover unbiased distributions and thus prevent models from capturing the two types of biases. Unfortunately, they either suffer from the extra cost of data collection/selection/annotation or need an elaborate design of balancing strategies. Different from traditional factual inference in which debiasing occurs before or during training, counterfactual inference mitigates the influence brought by unintended confounders after training, which can make unbiased decisions with biased observations. Inspired by this, we propose a model-agnostic text classification debiasing framework {--} Corsair, which can effectively avoid employing data manipulations or designing balancing mechanisms. Concretely, Corsair first trains a base model on a training set directly, allowing the dataset biases {`}poison{'} the trained model. In inference, given a factual input document, Corsair imagines its two counterfactual counterparts to distill and mitigate the two biases captured by the poisonous model. Extensive experiments demonstrate Corsair{'}s effectiveness, generalizability and fairness.

PaperPDFCode

Code

qianc62/corsair officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationCounterfactual InferenceFairnessText Classificationtext-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections