# One Probe Won't Catch Them All: Towards Targeted Deception Detection

arXiv: https://arxiv.org/abs/2602.01425 · HTML: https://mlsanity.com/paper/2602.01425/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability.
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Placed in

- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 12 of 12)

- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (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)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems](https://mlsanity.com/paper/2503.03750/) (2025)
- [Liars' Bench: Evaluating Lie Detectors for Language Models](https://mlsanity.com/paper/2511.16035/) (2025)
- [Benchmarking Deception Probes via Black-to-White Performance Boosts](https://mlsanity.com/paper/2507.12691/) (2025)

## Built on by (most cited first, 9 of 9)

- ["Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms](https://mlsanity.com/paper/2606.12618/) (2026)
- [What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models](https://mlsanity.com/paper/2608.16852/) (2026)
- [Do Linear Probes Generalize Better in Persona Coordinates?](https://mlsanity.com/paper/2605.09391/) (2026)
- [Asymmetries in Spontaneous and Instructed Deception](https://mlsanity.com/paper/2609.00180/) (2026)
- [The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes](https://mlsanity.com/paper/2609.10739/) (2026)
- [Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations](https://mlsanity.com/paper/2609.39807/) (2026)
- [Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception](https://mlsanity.com/paper/2610.12445/) (2026)
- [Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)](https://mlsanity.com/paper/2610.15314/) (2026)
- [On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination](https://mlsanity.com/paper/2610.18727/) (2026)

## Abstract (arXiv)

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However, these probes exhibit notable failures even in straightforward scenarios, including spurious correlations and false positives on non-deceptive responses. In this paper, we demonstrate that deception detection is inherently heterogeneous: while a single universal probe achieves modest improvements (+0.032 AUC), post-hoc oracle analysis reveals substantially higher potential (+0.108 AUC) when probes are matched to specific deception types, and synthetic validation experiments suggest this ceiling is achievable a priori when the deception type is known in advance. Our findings reveal that instruction pairs capture deceptive intent rather than content-specific patterns, explaining why prompt choice dominates probe performance (70.6% of variance). Given this heterogeneity, we conclude that organizations should define their specific threat models and deploy appropriately matched probes rather than seeking a universal deception detector.