Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this assumption with a direction-flipped influence audit: for each scenario, we compare a baseline prompt with matched cues steering toward option A or option B. Across a trolley-problem-style moral triage task, BBQ, and DailyDilemmas, and across five LLM families with and without reasoning, short contextual cues shift per-condition choice rates by 12-18 percentage points on average. These shifts reveal structure that baseline scores miss: roughly 40% of baseline-neutral triage and BBQ conditions exhibit directional asymmetry under influence, and a meaningful share of significant effects backfire, moving opposite the cue's intended direction. In follow-up probes, models often recognize the cue while denying that it affected their choice. Among significant backfire trials, this stated-vs.-revealed inconsistency appears in 78% of cases. Reasoning does not eliminate contextual sensitivity but reshapes it: social-pressure cues such as user preference and emotional appeal weaken across benchmarks, while few-shot demonstrations strengthen sharply on both triage and BBQ. We recommend direction-flipped influence pairs as a standard complement to context-free moral-bias evaluation, and release the harness and data to make such audits routine.

翻译：针对大型语言模型（LLM）的道德基准测试通常通过无上下文提示对模型进行评分，隐含地假设测量的选择率是稳定的。我们通过方向翻转影响审计来检验这一假设：针对每个场景，我们将基线提示与引导至选项A或选项B的匹配线索进行比较。在电车难题式道德分类任务、BBQ和DailyDilemmas数据集上，以及五个含推理与不含推理的LLM家族中，短上下文线索使各条件下的选择率平均变化12-18个百分点。这些变化揭示了基线得分所遗漏的结构：约40%的基线中性分类和BBQ条件在影响下表现出方向不对称性，且相当一部分显著效应适得其反，与线索的预期方向相反。在后续探查中，模型常能识别线索，却否认其影响了自身选择。在显著逆火试验中，这种陈述与揭示的不一致性出现在78%的案例中。推理并未消除上下文敏感性，但重塑了它：用户偏好和情感诉求等社会压力线索在基准测试中影响力减弱，而少样本示例在分类任务和BBQ上均显著增强。我们建议将方向翻转影响对作为无上下文道德偏差评估的标准补充，并发布相关工具包和数据，使此类审计成为常规操作。