GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German

• URL: http://arxiv.org/abs/2605.30214v1
• Date: Thu, 28 May 2026 16:47:46 GMT
• Title: GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German
• Abstract summary: We use a novel, large-scale dataset, GRUFF, to measure pronoun fidelity in German.<n>We show that LLMs show strong grammatical agreement for masculine and feminine entities in the absence of explicit context.<n>We also show that occupational stereotypes in this context are poorly correlated across grammatical cases.
• Score: 21.704876993752478
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with the task of pronoun fidelity, which assesses models' abilities to correctly reuse a previously-specified pronoun for a discourse entity, independent of other potentially distracting discourse entities mentioned in between. However, such research focuses on English, which is a language with limited grammatical gender and almost no gender agreement. In this paper we contribute a novel, large-scale dataset, GRUFF, to measure pronoun fidelity in German, covering four different gender agreement systems in nouns, and four sets of pronouns. With this dataset, we show that LLMs show strong grammatical agreement for masculine and feminine entities in the absence of explicit context, but not for neopronouns xier and en. Models are generally not robust to distractors, but encoder-only models are more robust in German than in English, reflecting the importance of grammatical gender. Finally, we show that occupational stereotypes in this context are poorly correlated across grammatical cases, and across most models, except ones with closely related architectures. We release all code and data to encourage further work on gender-inclusive language and referential reasoning in German.

Related papers

• EuroGEST: Investigating gender stereotypes in multilingual language models [58.871032460235575]
  We introduce EuroGEST, a dataset designed to measure gender-stereotypical reasoning in LLMs across English and 29 European languages.<n>We show that the strongest stereotypes in all models across all languages are that women are 'beautiful', 'empathetic' and 'neat' and men are 'leaders','strong, tough' and 'professional'
  arXiv  Detail & Related papers  (2025-06-04T11:58:18Z)
• What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages [51.0349882045866]
  This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. We prompt a model to describe nouns with adjectives in various languages, focusing specifically on languages with grammatical gender. We find that a simple classifier can not only predict noun gender above chance but also exhibit cross-language transferability.
  arXiv  Detail & Related papers  (2024-07-12T22:10:16Z)
• Building Bridges: A Dataset for Evaluating Gender-Fair Machine Translation into German [17.924716793621627]
  We study gender-fair language in English-to-German machine translation (MT) We conduct the first benchmark study involving two commercial systems and six neural MT models. Our findings show that most systems produce mainly masculine forms and rarely gender-neutral variants.
  arXiv  Detail & Related papers  (2024-06-10T09:39:19Z)
• Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased? [26.583741801345507]
  We present a dataset of over 5 million instances to measure pronoun fidelity in English. Our results show that pronoun fidelity is not robust, in a simple, naturalistic setting where humans achieve nearly 100% accuracy.
  arXiv  Detail & Related papers  (2024-04-04T01:07:14Z)
• The Causal Influence of Grammatical Gender on Distributional Semantics [87.8027818528463]
  How much meaning influences gender assignment across languages is an active area of research in linguistics and cognitive science. We offer a novel, causal graphical model that jointly represents the interactions between a noun's grammatical gender, its meaning, and adjective choice. When we control for the meaning of the noun, the relationship between grammatical gender and adjective choice is near zero and insignificant.
  arXiv  Detail & Related papers  (2023-11-30T13:58:13Z)
• How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation [21.125217707038356]
  When translating from notional gender languages into grammatical gender languages, the generated translation requires explicit gender assignments for various words, including those referring to the speaker. To avoid such biased and not inclusive behaviors, the gender assignment of speaker-related expressions should be guided by externally-provided metadata about the speaker's gender. This paper aims to achieve the same results by integrating the speaker's gender metadata into a single "multi-gender" neural ST model, easier to maintain.
  arXiv  Detail & Related papers  (2023-10-23T17:21:32Z)
• 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)
• MISGENDERED: Limits of Large Language Models in Understanding Pronouns [46.276320374441056]
  We evaluate popular language models for their ability to correctly use English gender-neutral pronouns. We introduce MISGENDERED, a framework for evaluating large language models' ability to correctly use preferred pronouns.
  arXiv  Detail & Related papers  (2023-06-06T18:27:52Z)
• How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns [0.15293427903448023]
  We show that gender-neutral pronouns (in Swedish) are not associated with human processing difficulties. We show that gender-neutral pronouns in Danish, English, and Swedish are associated with higher perplexity, more dispersed attention patterns, and worse downstream performance.
  arXiv  Detail & Related papers  (2022-04-11T09:42:02Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

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.