# Safer Policy Compliance with Dynamic Epistemic Fallback

arXiv: https://arxiv.org/abs/2601.23094 · HTML: https://mlsanity.com/paper/2601.23094/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 47 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 30 of 36)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Poisoning Retrieval Corpora by Injecting Adversarial Passages](https://mlsanity.com/paper/2310.19156/) (2023)
- [Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models](https://mlsanity.com/paper/2307.01379/) (2023)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models](https://mlsanity.com/paper/2302.13439/) (2023)
- [International AI Safety Report](https://mlsanity.com/paper/2501.17805/) (2025)
- [Monitoring Monitorability](https://mlsanity.com/paper/2512.18311/) (2025)
- [Attacking Open-domain Question Answering by Injecting Misinformation](https://mlsanity.com/paper/2110.07803/) (2021)
- [Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models](https://mlsanity.com/paper/2307.10236/) (2023)
- [GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory](https://mlsanity.com/paper/2406.11149/) (2024)
- [PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance](https://mlsanity.com/paper/2502.17041/) (2025)
- [Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?](https://mlsanity.com/paper/2505.24778/) (2025)
- [From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty](https://mlsanity.com/paper/2407.06071/) (2024)

## Built on by (most cited first, 1 of 1)

- [Sycophancy Undermines Epistemic Vigilance in Cooperative Vision-Language Tasks](https://mlsanity.com/paper/2607.29585/) (2026)

## Abstract (arXiv)

Humans develop a series of cognitive defenses, known as epistemic vigilance, to combat risks of deception and misinformation from everyday interactions. Developing safeguards for LLMs inspired by this mechanism might be particularly helpful for their application in high-stakes tasks such as automating compliance with data privacy laws. In this paper, we introduce Dynamic Epistemic Fallback (DEF), a dynamic safety protocol for improving an LLM's inference-time defenses against deceptive attacks that make use of maliciously perturbed policy texts. Through various levels of one-sentence textual cues, DEF nudges LLMs to flag inconsistencies, refuse compliance, and fallback to their parametric knowledge upon encountering perturbed policy texts. Using globally recognized legal policies such as HIPAA and GDPR, our empirical evaluations report that DEF effectively improves the capability of frontier LLMs to detect and refuse perturbed versions of policies, with DeepSeek-R1 achieving a 100% detection rate in one setting. This work encourages further efforts to develop cognitively inspired defenses to improve LLM robustness against forms of harm and deception that exploit legal artifacts.