# A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia

arXiv: https://arxiv.org/abs/2410.15464 · HTML: https://mlsanity.com/paper/2410.15464/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 20 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [ToxCCIn: Toxic Content Classification with Interpretability](https://mlsanity.com/paper/2103.01328/) (2021)

## Built on by (most cited first, 2 of 2)

- [Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages](https://mlsanity.com/paper/2506.07249/) (2025)
- [Social Bias in Multilingual Language Models: A Survey](https://mlsanity.com/paper/2508.20201/) (2025)

## Abstract (arXiv)

Work on bias in pretrained language models (PLMs) focuses on bias evaluation and mitigation and fails to tackle the question of bias attribution and explainability. We propose a novel metric, the textitbias attribution score, which draws from information theory to measure token-level contributions to biased behavior in PLMs. We then demonstrate the utility of this metric by applying it on multilingual PLMs, including models from Southeast Asia which have not yet been thoroughly examined in bias evaluation literature. Our results confirm the presence of sexist and homophobic bias in Southeast Asian PLMs. Interpretability and semantic analyses also reveal that PLM bias is strongly induced by words relating to crime, intimate relationships, and helping among other discursive categories, suggesting that these are topics where PLMs strongly reproduce bias from pretraining data and where PLMs should be used with more caution.