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

• URL: http://arxiv.org/abs/2506.07249v1
• Date: Sun, 08 Jun 2025 18:13:18 GMT
• Title: Bias Attribution in Filipino Language Models: Extending a Bias Interpretability Metric for Application on Agglutinative Languages
• Authors: Lance Calvin Lim Gamboa, Yue Feng, Mark Lee,
• Abstract summary: We adapt the information-theoretic bias attribution score metric for implementation on language models.<n>We show that Filipino models are driven towards bias by words pertaining to people, objects, and relationships.<n>These findings point to differences in how English and non-English models process inputs linked to sociodemographic groups and bias.
• Score: 8.58480189544444
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models [49.41113560646115]
  We investigate various proxy measures of bias in large language models (LLMs)<n>We find that evaluating models with pre-prompted personae on a multi-subject benchmark (MMLU) leads to negligible and mostly random differences in scores.<n>With the recent trend for LLM assistant memory and personalization, these problems open up from a different angle.
  arXiv  Detail & Related papers  (2025-06-12T08:47:40Z)
• Filipino Benchmarks for Measuring Sexist and Homophobic Bias in Multilingual Language Models from Southeast Asia [0.3376269351435396]
  We introduce benchmarks that assess both sexist and anti-queer biases in pretrained language models handling texts in Filipino.<n>The benchmarks consist of 7,074 new challenge pairs resulting from our cultural adaptation of English bias evaluation datasets.<n>We find that for multilingual models, the extent of bias learned for a particular language is influenced by how much pretraining data in that language a model was exposed to.
  arXiv  Detail & Related papers  (2024-12-10T08:31:52Z)
• A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia [0.3376269351435396]
  We propose a novel metric to measure token-level contributions to biased behavior in pretrained language models (PLMs) 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.
  arXiv  Detail & Related papers  (2024-10-20T18:31:05Z)
• Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models [50.40276881893513]
  This study introduces Spoken Stereoset, a dataset specifically designed to evaluate social biases in Speech Large Language Models (SLLMs) By examining how different models respond to speech from diverse demographic groups, we aim to identify these biases. The findings indicate that while most models show minimal bias, some still exhibit slightly stereotypical or anti-stereotypical tendencies.
  arXiv  Detail & Related papers  (2024-08-14T16:55:06Z)
• Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You [64.74707085021858]
  We show that multilingual models suffer from significant gender biases just as monolingual models do.<n>We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models.<n>Our results show that not only do models exhibit strong gender biases but they also behave differently across languages.
  arXiv  Detail & Related papers  (2024-01-29T12:02:28Z)
• Social Bias Probing: Fairness Benchmarking for Language Models [38.180696489079985]
  This paper proposes a novel framework for probing language models for social biases by assessing disparate treatment. We curate SoFa, a large-scale benchmark designed to address the limitations of existing fairness collections. We show that biases within language models are more nuanced than acknowledged, indicating a broader scope of encoded biases than previously recognized.
  arXiv  Detail & Related papers  (2023-11-15T16:35:59Z)
• Exposing Bias in Online Communities through Large-Scale Language Models [3.04585143845864]
  This work uses the flaw of bias in language models to explore the biases of six different online communities. The bias of the resulting models is evaluated by prompting the models with different demographics and comparing the sentiment and toxicity values of these generations. This work not only affirms how easily bias is absorbed from training data but also presents a scalable method to identify and compare the bias of different datasets or communities.
  arXiv  Detail & Related papers  (2023-06-04T08:09:26Z)
• Comparing Biases and the Impact of Multilingual Training across Multiple Languages [70.84047257764405]
  We present a bias analysis across Italian, Chinese, English, Hebrew, and Spanish on the downstream sentiment analysis task. We adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for four attributes: race, religion, nationality, and gender. Our results reveal similarities in bias expression such as favoritism of groups that are dominant in each language's culture.
  arXiv  Detail & Related papers  (2023-05-18T18:15:07Z)
• An Analysis of Social Biases Present in BERT Variants Across Multiple Languages [0.0]
  We investigate the bias present in monolingual BERT models across a diverse set of languages. We propose a template-based method to measure any kind of bias, based on sentence pseudo-likelihood. We conclude that current methods of probing for bias are highly language-dependent.
  arXiv  Detail & Related papers  (2022-11-25T23:38:08Z)
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models [22.57309958548928]
  We investigate whether structural supervision improves language models' ability to learn grammatical dependencies in typologically different languages. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and generative parsing models on datasets of different sizes. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings.
  arXiv  Detail & Related papers  (2021-09-22T22:11:30Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment [59.995385574274785]
  We show that, contrary to previous belief, negative interference also impacts low-resource languages. We present a meta-learning algorithm that obtains better cross-lingual transferability and alleviates negative interference.
  arXiv  Detail & Related papers  (2020-10-06T20:48:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.