# DECOR: Auditing LLM Deception via Information Manipulation Theory

arXiv: https://arxiv.org/abs/2605.19270 · HTML: https://mlsanity.com/paper/2605.19270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 26 of 26)

- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions](https://mlsanity.com/paper/2309.15840/) (2023)
- [CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring](https://mlsanity.com/paper/2505.23575/) (2025)
- [AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents](https://mlsanity.com/paper/2409.09013/) (2024)
- [DarkBench: Benchmarking Dark Patterns in Large Language Models](https://mlsanity.com/paper/2503.10728/) (2025)
- [BeHonest: Benchmarking Honesty in Large Language Models](https://mlsanity.com/paper/2406.13261/) (2024)
- [LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models](https://mlsanity.com/paper/2504.10430/) (2025)
- [Human Decision-making is Susceptible to AI-driven Manipulation](https://mlsanity.com/paper/2502.07663/) (2025)
- [Towards eliciting latent knowledge from LLMs with mechanistic interpretability](https://mlsanity.com/paper/2505.14352/) (2025)
- [When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models](https://mlsanity.com/paper/2506.04909/) (2025)
- [When Do Large Language Models Exhibit Unsolicited Deception?](https://mlsanity.com/paper/2504.00285/) (2025)
- [Constitutional Black-Box Monitoring for Scheming in LLM Agents](https://mlsanity.com/paper/2603.00829/) (2026)
- [Can LLMs Lie? Investigation beyond Hallucination](https://mlsanity.com/paper/2509.03518/) (2025)
- [LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions](https://mlsanity.com/paper/2510.03999/) (2025)
- [AI Deception: Risks, Dynamics, and Controls](https://mlsanity.com/paper/2511.22619/) (2025)
- [Evaluating Language Models for Harmful Manipulation](https://mlsanity.com/paper/2603.25326/) (2026)
- [Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts](https://mlsanity.com/paper/2508.06361/) (2025)
- [Detecting Malicious AI Agents Through Simulated Interactions](https://mlsanity.com/paper/2504.03726/) (2025)

## Abstract (arXiv)

Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detect. Existing black-box methods rely on coarse-grained judgments, offering limited interpretability and failing to pinpoint which facts were distorted and how. We introduce DECOR, a multi-agent framework grounded in Information Manipulation Theory for fine-grained auditing of strategic deception in LLM responses. DECOR decomposes input contexts into atomic informational units and scores each unit against the response across four dimensions of manipulation, producing interpretable manipulation profiles that are aggregated into a global deception index. We comprehensively evaluate DECOR on both single-turn and multi-turn deception detection benchmarks spanning real-world domains, and show that DECOR achieves state-of-the-art performance on both, outperforming competitive baselines. The framework generalizes across 15 frontier models, and ablation studies confirm the contribution of each key design component. Our findings demonstrate that fine-grained, theory-grounded auditing of information manipulation offers an effective and interpretable path for LLM deception detection.