# What About the Scene with the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency Via Adversarial Nudge

arXiv: https://arxiv.org/abs/2511.08596 · HTML: https://mlsanity.com/paper/2511.08596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2025.

## Abstract (arXiv)

Hallucinations pose a critical challenge to the real-world deployment of large language models (LLMs) in high-stakes domains. In this paper, we present a framework for stress testing factual fidelity in LLMs in the presence of adversarial nudge. Our framework consists of three steps. In the first step, we instruct the LLM to produce sets of truths and lies consistent with the closed domain in question. In the next step, we instruct the LLM to verify the same set of assertions as truths and lies consistent with the same closed domain. In the final step, we test the robustness of the LLM against the lies generated (and verified) by itself. Our extensive evaluation, conducted using five widely known proprietary LLMs across two closed domains of popular movies and novels, reveals a wide range of susceptibility to adversarial nudges: textttClaude exhibits strong resilience, textttGPT and textttGrok demonstrate moderate resilience, while textttGemini and textttDeepSeek show weak resilience. Considering that a large population is increasingly using LLMs for information seeking, our findings raise alarm.