arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.22720cs.AIcs.HC
收藏

AI 是否会加剧冲突?在冲突情境下LLM部署中的对齐失败

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

Independent Researcher(独立研究者)

Andrii Kryshtal

AI总结:

本文研究了AI模型在冲突情境下可能产生的对齐失败问题,通过测试九种模型配置,发现其在处理冲突相关场景时存在错误等价、否认种族灭绝和未能识别种族歧视术语等问题,提出了首个评估框架以提高AI在冲突情境下的安全性。

摘要:

AI模型已经部署在受武装冲突影响的社会中,记者、人道主义工作者、政府和普通公民依赖这些模型获取信息或用于工作流程。目前尚无已建立的实践来检查其输出是否会加剧冲突。我们测试了来自四个供应商(OpenAI、Anthropic、DeepSeek、xAI)的九种模型配置,在90个多轮场景中揭示了冲突情境中的对齐失败行为:如在记录的暴行之间制造虚假等价、否认种族灭绝以及未能识别种族歧视术语等。当这些输出影响新闻报道、人道主义报告或公共辩论时,它们可能加深脆弱社会的分歧。失败率在最佳和最差表现的模型之间为6%至47%,这使得模型选择本身成为一项安全问题。当用户在国际法院已指责任任的情况下寻求“平衡”时,五种配置在80%至100%的情况下失败。我们发布了该领域的首个评估框架,并建议将其添加到对齐评估套件中。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑