# Same violence, different answer: how AI responds to coercive control against women across languages

arXiv: https://arxiv.org/abs/2608.01436 · HTML: https://mlsanity.com/paper/2608.01436/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With](https://mlsanity.com/paper/2104.04052/) (2021)
- [Cross-lingual Transfer of Reward Models in Multilingual Alignment](https://mlsanity.com/paper/2410.18027/) (2024)
- [Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment](https://mlsanity.com/paper/2505.21548/) (2025)
- [Online Misogyny Against Female Candidates in the 2022 Brazilian Elections: A Threat to Women's Political Representation?](https://mlsanity.com/paper/2403.07523/) (2024)
- [Introducing DictaLM -- A Large Generative Language Model for Modern Hebrew](https://mlsanity.com/paper/2309.14568/) (2023)
- [Assessing LLM Response Quality in the Context of Technology-Facilitated Abuse](https://mlsanity.com/paper/2602.17672/) (2026)

## Abstract (arXiv)

Women experiencing coercive control, a form of intimate partner violence increasingly conducted through digital devices, are turning to conversational AI for help, and the protection they receive should not depend on the language they write in. We analyse how AI responds to coercive control against women across languages. We put one scripted scenario to seven widely used language models in nine languages: a woman whose partner tracks her phone asks for help with a self-blaming letter accepting the surveillance. We scored whether the model wrote the letter and whether it named the control, countered the self-blame, and affirmed her agency. Failure split along two independent axes. On the first, systems from non-anglophone developers gave way most often in their builders' own language. On the second, how far a sympathetic excuse for the partner could strip a model's naming of the control varied sharply from one language to the next. Two frontier systems held the strictest standard everywhere, so a protective ceiling is attainable within this scenario family, and failures elsewhere are a design outcome. What is at stake is recognition: whether a system grasps a disclosure as coercive control, and whether it then acts on that grasp. We argue this should be held to a floor, one language at a time.