Abstract
This paper proposes a trustworthy computational method to gender-swap public domain novels, with programmatic guarantees that only gendered words are inverted and all other words are left unchanged. This may seem like a simple task, but both large language models and naive rule-based methods fail to complete it. The proposed method includes a custom whitespace-preserving tokenizer, gender-swap mappings across plural and possessive forms, pronoun handling, and a character renaming strategy. It shortens the time required to gender-swap a novel from weeks of manual labor to minutes. The method is demonstrated on two public-domain novels. Pride and Prejudice is transported to matriarchal Regency England, where inheritance flows through daughters, mothers rule the household, and a frantic Mr. Bennet is determined to secure advantageous marriages for his sons. The Great Gatsby pivots to a matriarchal Jazz Age where newly-rich Ms. Gatsbee throws lavish parties in the hopes of reuniting with her lost love, David, who is now married to the violent Thelma Buchanan. Gender-swapped novels could serve as useful tools to investigate the gender biases of readers, authors, societies, and AI systems.
More in this topicComputational Literary Studies uses data analysis and language technologies to examine literary style, themes, narratives, influence, and change.
See all 53 papers → Mar 29, 2026
We introduce ProText, a dataset for measuring gendering and misgendering in stylistically diverse long-form English texts. ProText spans three dimensions: Theme nouns (names, occupations, titles, kinship terms), Theme category (stereotypically male, stereotypically female, gender-neutral/non-gendered), and Pronoun category (masculine, feminine, gender-neutral, none). The dataset is designed to probe (mis)gendering in text transformations such as summarization and rewrites using state-of-the-art Large Language Models, extending beyond traditional pronoun resolution benchmarks and beyond the gender binary. We validated ProText through a mini case study, showing that even with just two prompts and two models, we can draw nuanced insights regarding gender bias, stereotyping, misgendering, and gendering. We reveal systematic gender bias, particularly when inputs contain no explicit gender cues or when models default to heteronormative assumptions.
Hadas Kotek, Margit Bowler, Patrick Sonnenberg +1
Apple, USA
May 9, 2026
The diachronic evolution from Latin to the Romance languages involved a restructuring of the grammatical gender system from a tripartite configuration (masculine, feminine, neuter) to a bipartite one (masculine, feminine) in most Romance languages. In this work, we introduce an interpretable deep learning framework to investigate this phenomenon at both lexical and contextual levels. First, we show that conventional tokenization strategies are insufficiently robust for this low-resource historical setting, and that our proposed tokenizer improves performance over these baselines. At the lexical level, we evaluate the contribution of morphological features to gender prediction. At the contextual level, we quantify the contributions of different part-of-speech categories to grammatical gender prediction. Together, these analyses characterize the distribution of gender information between the lemma and its sentential context. We make our codebase, datasets, and results publicly available at https://github.com/ahan-2000/Lost-in-Translation-.
Ahan Chatterjee, Matthias Schöffel, Matthias Aßenmacher +2
Bavarian Academy of Sciences (BAdW), Munich · LMU Munich · Munich Center for Machine Learning (MCML) +1
Mar 18, 2026
While Large Language Models achieve state-of-the-art results across a wide range of NLP tasks, they remain prone to systematic biases. Among these, gender bias is particularly salient in MT, due to systematic differences across languages in whether and how gender is marked. As a result, translation often requires disambiguating implicit source signals into explicit gender-marked forms. In this context, standard benchmarks may capture broad disparities but fail to reflect the full complexity of gender bias in modern MT. In this paper, we extend recent frameworks on bias evaluation by: (i) introducing a novel measure coined "Prior Bias", capturing a model's default gender assumptions, and (ii) applying the framework to decoder-only MT models. Our results show that, despite their scale and state-of-the-art status, decoder-only models do not generally outperform encoder-decoder architectures on gender-specific metrics; however, post-training (e.g., instruction tuning) not only improves contextual awareness but also reduces the masculine Prior Bias.
Chiara Manna, Hosein Mohebbi, Afra Alishahi +2
Research Center for Cognitive Science and Artificial Intelligence Tilburg School of Humanities and Digital Sciences Tilburg University, Netherlands