# Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages

arXiv: https://arxiv.org/abs/2506.07249 · HTML: https://mlsanity.com/paper/2506.07249/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Improving Large-scale Language Models and Resources for Filipino](https://mlsanity.com/paper/2111.06053/) (2021)
- [From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models](https://mlsanity.com/paper/2403.03893/) (2024)
- [Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques](https://mlsanity.com/paper/2310.10310/) (2023)
- [ToxCCIn: Toxic Content Classification with Interpretability](https://mlsanity.com/paper/2103.01328/) (2021)
- [Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models](https://mlsanity.com/paper/2311.01732/) (2023)
- [Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia](https://mlsanity.com/paper/2412.07303/) (2024)
- [Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech](https://mlsanity.com/paper/2204.07661/) (2022)
- [A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia](https://mlsanity.com/paper/2410.15464/) (2024)

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

- [Social Bias in Multilingual Language Models: A Survey](https://mlsanity.com/paper/2508.20201/) (2025)
- [Robust Bias Evaluation with FilBBQ: A Filipino Bias Benchmark for Question-Answering Language Models](https://mlsanity.com/paper/2602.14466/) (2026)

## Abstract (arXiv)

Emerging research on bias attribution and interpretability have revealed how tokens contribute to biased behavior in language models processing English texts. We build on this line of inquiry by adapting the information-theoretic bias attribution score metric for implementation on models handling agglutinative languages, particularly Filipino. We then demonstrate the effectiveness of our adapted method by using it on a purely Filipino model and on three multilingual models: one trained on languages worldwide and two on Southeast Asian data. Our results show that Filipino models are driven towards bias by words pertaining to people, objects, and relationships, entity-based themes that stand in contrast to the action-heavy nature of bias-contributing themes in English (i.e., criminal, sexual, and prosocial behaviors). These findings point to differences in how English and non-English models process inputs linked to sociodemographic groups and bias.