# Truth is Universal: Robust Detection of Lies in LLMs

arXiv: https://arxiv.org/abs/2407.12831 · HTML: https://mlsanity.com/paper/2407.12831/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Explore, Establish, Exploit: Red Teaming Language Models from Scratch](https://mlsanity.com/paper/2306.09442/) (2023)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions](https://mlsanity.com/paper/2309.15840/) (2023)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant](https://mlsanity.com/paper/2405.01576/) (2024)

## Built on by (most cited first, 30 of 79)

- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry](https://mlsanity.com/paper/2503.01822/) (2025)
- [Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding](https://mlsanity.com/paper/2502.01563/) (2025)
- [No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes](https://mlsanity.com/paper/2509.10625/) (2025)
- [Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer](https://mlsanity.com/paper/2502.12964/) (2025)
- [How do LLMs Compute Verbal Confidence](https://mlsanity.com/paper/2603.17839/) (2026)
- [Benchmarking Deception Probes via Black-to-White Performance Boosts](https://mlsanity.com/paper/2507.12691/) (2025)
- [Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks](https://mlsanity.com/paper/2506.00823/) (2025)
- [Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives](https://mlsanity.com/paper/2511.06626/) (2025)
- [LLMScan: Causal Scan for LLM Misbehavior Detection](https://mlsanity.com/paper/2410.16638/) (2024)
- [Difficulties with Evaluating a Deception Detector for AIs](https://mlsanity.com/paper/2511.22662/) (2025)
- [How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence](https://mlsanity.com/paper/2504.02904/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Emergence of Linear Truth Encodings in Language Models](https://mlsanity.com/paper/2510.15804/) (2025)
- [The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes](https://mlsanity.com/paper/2602.15515/) (2026)
- [Representation Potentials of Foundation Models for Multimodal Alignment: A Survey](https://mlsanity.com/paper/2510.05184/) (2025)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [When Truthful Representations Flip Under Deceptive Instructions?](https://mlsanity.com/paper/2507.22149/) (2025)
- [LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit](https://mlsanity.com/paper/2604.19117/) (2026)
- [Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective](https://mlsanity.com/paper/2412.12276/) (2024)
- [Preference Learning with Lie Detectors can Induce Honesty or Evasion](https://mlsanity.com/paper/2505.13787/) (2025)
- [Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs](https://mlsanity.com/paper/2508.19432/) (2025)
- [Prompt-Guided Internal States for Hallucination Detection of Large Language Models](https://mlsanity.com/paper/2411.04847/) (2024)
- [The Truthfulness Spectrum Hypothesis](https://mlsanity.com/paper/2602.20273/) (2026)
- [PredictaBoard: Benchmarking LLM Score Predictability](https://mlsanity.com/paper/2502.14445/) (2025)
- [Can LLMs Lie? Investigation beyond Hallucination](https://mlsanity.com/paper/2509.03518/) (2025)
- [Position: Anthropomorphic Misalignment Research Needs Stronger Evidence](https://mlsanity.com/paper/2606.07612/) (2026)
- [Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations](https://mlsanity.com/paper/2504.13816/) (2025)
- [HACK: Hallucinations Along Certainty and Knowledge Axes](https://mlsanity.com/paper/2510.24222/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have revolutionised natural language processing, exhibiting impressive human-like capabilities. In particular, LLMs are capable of "lying", knowingly outputting false statements. Hence, it is of interest and importance to develop methods to detect when LLMs lie. Indeed, several authors trained classifiers to detect LLM lies based on their internal model activations. However, other researchers showed that these classifiers may fail to generalise, for example to negated statements. In this work, we aim to develop a robust method to detect when an LLM is lying. To this end, we make the following key contributions: (i) We demonstrate the existence of a two-dimensional subspace, along which the activation vectors of true and false statements can be separated. Notably, this finding is universal and holds for various LLMs, including Gemma-7B, LLaMA2-13B, Mistral-7B and LLaMA3-8B. Our analysis explains the generalisation failures observed in previous studies and sets the stage for more robust lie detection; (ii) Building upon (i), we construct an accurate LLM lie detector. Empirically, our proposed classifier achieves state-of-the-art performance, attaining 94% accuracy in both distinguishing true from false factual statements and detecting lies generated in real-world scenarios.