# How User Language Affects Conflict Fatality Estimates in ChatGPT

arXiv: https://arxiv.org/abs/2308.00072 · HTML: https://mlsanity.com/paper/2308.00072/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 122 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 11 of 11)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets](https://mlsanity.com/paper/2103.12028/) (2021)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [ChatGPT: Applications, Opportunities, and Threats](https://mlsanity.com/paper/2304.09103/) (2023)
- [Does Corpus Quality Really Matter for Low-Resource Languages?](https://mlsanity.com/paper/2203.08111/) (2022)

## Built on by (most cited first, 4 of 4)

- [Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights](https://mlsanity.com/paper/2502.19463/) (2025)
- [Analysing LLM Persona Generation and Fairness Interpretation in Polarised Geopolitical Contexts](https://mlsanity.com/paper/2603.22837/) (2026)
- [Are LLMs Ready for Conflict Monitoring? Empirical Evidence from West Africa](https://mlsanity.com/paper/2605.04177/) (2026)
- [Geopolitical Divisions Across Languages in Large Language Models](https://mlsanity.com/paper/2609.20005/) (2026)

## Abstract (arXiv)

OpenAI's ChatGPT language model has gained popularity as a powerful tool for complex problem-solving and information retrieval. However, concerns arise about the reproduction of biases present in the language-specific training data. In this study, we address this issue in the context of the Israeli-Palestinian and Turkish-Kurdish conflicts. Using GPT-3.5, we employed an automated query procedure to inquire about casualties in specific airstrikes, in both Hebrew and Arabic for the former conflict and Turkish and Kurdish for the latter. Our analysis reveals that GPT-3.5 provides 27±11 percent lower fatality estimates when queried in the language of the attacker than in the language of the targeted group. Evasive answers denying the existence of such attacks further increase the discrepancy, creating a novel bias mechanism not present in regular search engines. This language bias has the potential to amplify existing media biases and contribute to information bubbles, ultimately reinforcing conflicts.