# Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict Contexts

arXiv: https://arxiv.org/abs/2605.22720 · HTML: https://mlsanity.com/paper/2605.22720/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 4 of 4)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models](https://mlsanity.com/paper/2503.06263/) (2025)
- [Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models](https://mlsanity.com/paper/2506.06751/) (2025)

## Abstract (arXiv)

AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for checking whether their outputs can make those conflicts worse. We tested nine model configurations from four providers (OpenAI, Anthropic, DeepSeek, xAI) on 90 multi-turn scenarios designed to surface misaligned behaviour in conflict contexts: false equivalence between documented atrocities, denial of genocide, and failure to recognise ethnic slurs, among others. When such outputs feed into journalism, humanitarian reporting, or public debate, they can deepen divisions in fragile societies. Failure rates span 6% to 47% between the best and worst performing models, which makes model choice a safety question in its own right and when users pushed for ``balance'' in cases where international courts have already assigned responsibility, five of nine configurations failed 80 to 100 percent of the time. We release the first evaluation framework for this domain and propose adding it to alignment evaluation portfolios.