# Towards Massive Multilingual Holistic Bias

arXiv: https://arxiv.org/abs/2407.00486 · HTML: https://mlsanity.com/paper/2407.00486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 29 Jun 2024.

## Builds on (most cited first, 30 of 30)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation](https://mlsanity.com/paper/2109.03858/) (2021)
- [Perturbation Augmentation for Fairer NLP](https://mlsanity.com/paper/2205.12586/) (2022)
- [The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations](https://mlsanity.com/paper/2308.02053/) (2023)
- [AugLy: Data Augmentations for Robustness](https://mlsanity.com/paper/2201.06494/) (2022)
- [Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation](https://mlsanity.com/paper/2106.00169/) (2021)
- [Toxicity in Multilingual Machine Translation at Scale](https://mlsanity.com/paper/2210.03070/) (2022)
- [Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale](https://mlsanity.com/paper/2305.13198/) (2023)
- [Investigating Failures of Automatic Translation in the Case of Unambiguous Gender](https://mlsanity.com/paper/2104.07838/) (2021)
- [The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses](https://mlsanity.com/paper/2110.09216/) (2021)
- [Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters](https://mlsanity.com/paper/2012.13176/) (2020)
- [Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation](https://mlsanity.com/paper/2311.06532/) (2023)
- [The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages](https://mlsanity.com/paper/2308.16871/) (2023)

## Abstract (arXiv)

In the current landscape of automatic language generation, there is a need to understand, evaluate, and mitigate demographic biases as existing models are becoming increasingly multilingual. To address this, we present the initial eight languages from the MASSIVE MULTILINGUAL HOLISTICBIAS (MMHB) dataset and benchmark consisting of approximately 6 million sentences representing 13 demographic axes. We propose an automatic construction methodology to further scale up MMHB sentences in terms of both language coverage and size, leveraging limited human annotation. Our approach utilizes placeholders in multilingual sentence construction and employs a systematic method to independently translate sentence patterns, nouns, and descriptors. Combined with human translation, this technique carefully designs placeholders to dynamically generate multiple sentence variations and significantly reduces the human translation workload. The translation process has been meticulously conducted to avoid an English-centric perspective and include all necessary morphological variations for languages that require them, improving from the original English HOLISTICBIAS. Finally, we utilize MMHB to report results on gender bias and added toxicity in machine translation tasks. On the gender analysis, MMHB unveils: (1) a lack of gender robustness showing almost +4 chrf points in average for masculine semantic sentences compared to feminine ones and (2) a preference to overgeneralize to masculine forms by reporting more than +12 chrf points in average when evaluating with masculine compared to feminine references. MMHB triggers added toxicity up to 2.3%.