# Direction-Flipped Influence Audits Reveal Hidden Structure in Moral Choices of LLMs

arXiv: https://arxiv.org/abs/2602.22831 · HTML: https://mlsanity.com/paper/2602.22831/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2026.

## Built on by (most cited first, 3 of 3)

- [SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy](https://mlsanity.com/paper/2604.02423/) (2026)
- [A Virtuous AI is an Existential Risk](https://mlsanity.com/paper/2606.13739/) (2026)
- [Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning](https://mlsanity.com/paper/2606.15507/) (2026)

## Abstract (arXiv)

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.