A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation

• URL: http://arxiv.org/abs/2310.12127v2
• Date: Wed, 25 Oct 2023 13:43:49 GMT
• Title: A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
• Authors: Giuseppe Attanasio, Flor Miriam Plaza-del-Arco, Debora Nozza, Anne Lauscher
• Abstract summary: We investigate whether and to what extent machine translation models exhibit gender bias. We find that IFT models default to male-inflected translations, even disregarding female occupational stereotypes. We propose an easy-to-implement and effective bias mitigation solution.
• Score: 35.44115368160656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethical considerations behind. In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. Concretely, we compute established gender bias metrics on the WinoMT corpus from English to German and Spanish. We discover that IFT models default to male-inflected translations, even disregarding female occupational stereotypes. Next, using interpretability methods, we unveil that models systematically overlook the pronoun indicating the gender of a target occupation in misgendered translations. Finally, based on this finding, we propose an easy-to-implement and effective bias mitigation solution based on few-shot learning that leads to significantly fairer translations.

Related papers

• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Investigating Markers and Drivers of Gender Bias in Machine Translations [0.0]
  Implicit gender bias in large language models (LLMs) is a well-documented problem. We use the DeepL translation API to investigate the bias evinced when repeatedly translating a set of 56 Software Engineering tasks. We find that some languages display similar patterns of pronoun use, falling into three loose groups. We identify the main verb appearing in a sentence as a likely significant driver of implied gender in the translations.
  arXiv  Detail & Related papers  (2024-03-18T15:54:46Z)
• In-Contextual Gender Bias Suppression for Large Language Models [47.246504807946884]
  Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. We propose bias suppression that prevents biased generations of LLMs by providing preambles constructed from manually designed templates. We find that bias suppression has acceptable adverse effect on downstream task performance with HellaSwag and COPA.
  arXiv  Detail & Related papers  (2023-09-13T18:39:08Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation [28.471506840241602]
  Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. We propose a bias mitigation method based on a novel approach. Gender-Aware Contrastive Learning, GACL, encodes contextual gender information into the representations of non-explicit gender words.
  arXiv  Detail & Related papers  (2023-05-23T12:53:39Z)
• Testing Occupational Gender Bias in Language Models: Towards Robust Measurement and Zero-Shot Debiasing [98.07536837448293]
  Large language models (LLMs) have been shown to exhibit a variety of harmful, human-like biases against various demographics. We introduce a list of desiderata for robustly measuring biases in generative language models. We then use this benchmark to test several state-of-the-art open-source LLMs, including Llama, Mistral, and their instruction-tuned versions.
  arXiv  Detail & Related papers  (2022-12-20T22:41:24Z)
• How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts [11.684346035745975]
  A growing number of studies highlight the inherent gender bias that Neural Machine Translation models incorporate during training. We investigate whether these models can be instructed to fix their bias during inference using targeted, guided instructions as contexts. We observe large improvements in reducing the gender bias in translations, across three popular test suites.
  arXiv  Detail & Related papers  (2022-05-22T06:31:54Z)
• Mitigating Gender Bias in Machine Translation through Adversarial Learning [0.8883733362171032]
  We present an adversarial learning framework that addresses challenges to mitigate gender bias in seq2seq machine translation. Our framework improves the disparity in translation quality for sentences with male vs. female entities by 86% for English-German translation and 91% for English-French translation.
  arXiv  Detail & Related papers  (2022-03-20T23:35:09Z)
• Examining Covert Gender Bias: A Case Study in Turkish and English Machine Translation Models [7.648784748888186]
  We examine cases of both overt and covert gender bias in Machine Translation models. Specifically, we introduce a method to investigate asymmetrical gender markings. We also assess bias in the attribution of personhood and examine occupational and personality stereotypes.
  arXiv  Detail & Related papers  (2021-08-23T19:25:56Z)
• Decoding and Diversity in Machine Translation [90.33636694717954]
  We characterize differences between cost diversity paid for the BLEU scores enjoyed by NMT. Our study implicates search as a salient source of known bias when translating gender pronouns.
  arXiv  Detail & Related papers  (2020-11-26T21:09:38Z)

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.