Gender bias is not only prevalent in Large Language Models (LLMs) and their training data, but also firmly ingrained into the structural aspects of language itself. Therefore, adapting linguistic structures within LLM training data to promote gender-inclusivity can make gender representations within the model more inclusive.The focus of our work are gender-exclusive affixes in English, such as in ‘show-girl’ or ‘man-cave’, which can perpetuate gender stereotypes and binary conceptions of gender.We use an LLM training dataset to compile a catalogue of 692 gender-exclusive terms along with gender-neutral variants and from this, develop a gender-inclusive fine-tuning dataset, the ‘Tiny Heap’. Fine-tuning three different LLMs with this dataset, we observe an overall reduction in gender-stereotyping tendencies across the models. Our approach provides a practical method for enhancing gender inclusivity in LLM training data and contributes to incorporating queer-feminist linguistic activism in bias mitigation research in NLP.

This paper presents a new method for automatic detection of gendered terms in large-scale language datasets. Currently, the evaluation of gender bias in natural language processing relies on the use of manually compiled lexicons of gendered expressions, such as pronouns and words that imply gender. However, manual compilation of lists with lexical gender can lead to static information if lists are not periodically updated and often involve value judgements by individual annotators and researchers. Moreover, terms not included in the lexicons fall out of the range of analysis. To address these issues, we devised a scalable dictionary-based method to automatically detect lexical gender that can provide a dynamic, up-to-date analysis with high coverage. Our approach reaches over 80% accuracy in determining the lexical gender of words retrieved randomly from a Wikipedia sample and when testing on a list of gendered words used in previous research.

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to assess biases encoded in their replacements as well. Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions in English and German, comparing the findings with real-world workforce statistics. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018), after applying Counterfactual Data Substitution (CDS) (Maudslay et al., 2019). We show that our method of measuring bias is appropriate for languages such as English, but not for languages with a rich morphology and gender-marking, such as German. Our results highlight the importance of investigating bias and mitigation techniques cross-linguistically,especially in view of the current emphasis on large-scale, multilingual language models.