# When Distributions Shifts: Causal Generalization for Low-Resource Languages

arXiv: https://arxiv.org/abs/2510.27512 · HTML: https://mlsanity.com/paper/2510.27512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning](https://mlsanity.com/paper/2204.06487/) (2022)
- [Towards Debiasing Fact Verification Models](https://mlsanity.com/paper/1908.05267/) (2019)
- [AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages](https://mlsanity.com/paper/2302.08956/) (2023)
- [NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis](https://mlsanity.com/paper/2201.08277/) (2022)
- [The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks](https://mlsanity.com/paper/2304.13861/) (2023)
- [Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification](https://mlsanity.com/paper/1909.06276/) (2019)
- [Domain Generalization -- A Causal Perspective](https://mlsanity.com/paper/2209.15177/) (2022)
- [Where Are We? Evaluating LLM Performance on African Languages](https://mlsanity.com/paper/2502.19582/) (2025)
- [M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2502.11824/) (2025)
- [DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference](https://mlsanity.com/paper/2403.01166/) (2024)
- [A Deep Convolutional Neural Network-based Model for Aspect and Polarity Classification in Hausa Movie Reviews](https://mlsanity.com/paper/2405.19575/) (2024)
- [Improving Generative Cross-lingual Aspect-Based Sentiment Analysis with Constrained Decoding](https://mlsanity.com/paper/2508.10369/) (2025)

## Abstract (arXiv)

Machine learning models often fail under distribution shifts, a problem exacerbated in low-resource settings where limited data restricts robust generalization. Domain generalization(DG) methods address this challenge by learning representations that remain invariant across domains, frequently leveraging causal principles. In this work, we study two causal DG approaches for low-resource natural language processing. First, we apply causal data augmentation using GPT-4o-mini to generate counterfactual paraphrases for sentiment classification on the NaijaSenti Twitter corpus in Yoruba and Igbo. Second, we investigate invariant causal representation learning with the Debiasing in Aspect Review (DINER) framework for aspect-based sentiment analysis. We extend DINER to a multilingual setting by introducing Afri-SemEval, a dataset of 17 languages translated from SemEval-2014 Task. Experiments show improved robustness to unseen domains, with consistent gains from counterfactual augmentation and enhanced out-of-distribution performance from causal representation learning across multiple languages.