Measuring Harmful Representations in Scandinavian Language Models

• URL: http://arxiv.org/abs/2211.11678v1
• Date: Mon, 21 Nov 2022 17:46:39 GMT
• Title: Measuring Harmful Representations in Scandinavian Language Models
• Authors: Samia Touileb and Debora Nozza
• Abstract summary: We show that Scandinavian pre-trained language models contain harmful and gender-based stereotypes. This finding goes against the general expectations related to gender equality in Scandinavian countries.
• Score: 14.895663939509634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scandinavian countries are perceived as role-models when it comes to gender equality. With the advent of pre-trained language models and their widespread usage, we investigate to what extent gender-based harmful and toxic content exist in selected Scandinavian language models. We examine nine models, covering Danish, Swedish, and Norwegian, by manually creating template-based sentences and probing the models for completion. We evaluate the completions using two methods for measuring harmful and toxic completions and provide a thorough analysis of the results. We show that Scandinavian pre-trained language models contain harmful and gender-based stereotypes with similar values across all languages. This finding goes against the general expectations related to gender equality in Scandinavian countries and shows the possible problematic outcomes of using such models in real-world settings.

Related papers

• How Gender Interacts with Political Values: A Case Study on Czech BERT Models [0.0]
  This case study focuses on the political biases of pre-trained encoders in Czech. Because Czech is a gendered language, we measure how the grammatical gender coincides with responses to men and women in the survey. We find that the models do not assign statement probability following value-driven reasoning.
  arXiv  Detail & Related papers  (2024-03-20T11:30:45Z)
• 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. We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models. 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)
• Multilingual Conceptual Coverage in Text-to-Image Models [98.80343331645626]
  "Conceptual Coverage Across Languages" (CoCo-CroLa) is a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language.
  arXiv  Detail & Related papers  (2023-06-02T17:59:09Z)
• Measuring Gender Bias in West Slavic Language Models [41.49834421110596]
  We introduce the first template-based dataset in Czech, Polish, and Slovak for measuring gender bias towards male, female and non-binary subjects. We measure gender bias encoded in West Slavic language models by quantifying the toxicity and genderness of the generated words. We find that these language models produce hurtful completions that depend on the subject's gender.
  arXiv  Detail & Related papers  (2023-04-12T11:49:43Z)
• Measuring Normative and Descriptive Biases in Language Models Using Census Data [6.445605125467574]
  We investigate how occupations with respect to gender is reflected in pre-trained language models. We introduce an approach for measuring to what degree pre-trained language models are aligned to normative and descriptive occupational distributions.
  arXiv  Detail & Related papers  (2023-04-12T11:06:14Z)
• Do Multilingual Language Models Capture Differing Moral Norms? [71.52261949766101]
  Massively multilingual sentence representations are trained on large corpora of uncurated data. This may cause the models to grasp cultural values including moral judgments from the high-resource languages. The lack of data in certain languages can also lead to developing random and thus potentially harmful beliefs.
  arXiv  Detail & Related papers  (2022-03-18T12:26:37Z)
• Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation [10.542861450223128]
  We find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments in corpora from three domains. We manually verify the quality of our corpus and use it to evaluate gender bias in various coreference resolution and machine translation models.
  arXiv  Detail & Related papers  (2021-09-08T18:14:11Z)
• Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models [104.41668491794974]
  We quantify the usage of adjectives and verbs generated by language models surrounding the names of politicians as a function of their gender. We find that while some words such as dead, and designated are associated with both male and female politicians, a few specific words such as beautiful and divorced are predominantly associated with female politicians.
  arXiv  Detail & Related papers  (2021-04-15T15:03:26Z)
• 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)
• Word embedding and neural network on grammatical gender -- A case study of Swedish [0.5243215690489517]
  We show how the information about grammatical gender in language can be captured by word embedding models and artificial neural networks. We analyze the errors made by the computational model from a linguistic perspective.
  arXiv  Detail & Related papers  (2020-07-28T13:50:17Z)

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.