# Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)

arXiv: https://arxiv.org/abs/2610.15314 · HTML: https://mlsanity.com/paper/2610.15314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 11 Oct 2026.

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

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [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)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [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)
- [Conformal Prediction Under Covariate Shift](https://mlsanity.com/paper/1904.06019/) (2019)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [Overthinking the Truth: Understanding how Language Models Process False Demonstrations](https://mlsanity.com/paper/2307.09476/) (2023)
- [Transformers represent belief state geometry in their residual stream](https://mlsanity.com/paper/2405.15943/) (2024)
- [Detecting High-Stakes Interactions with Activation Probes](https://mlsanity.com/paper/2506.10805/) (2025)
- [Neyman-Pearson (NP) classification algorithms and NP receiver operating characteristics (NP-ROC)](https://mlsanity.com/paper/1608.03109/) (2016)
- [Liars' Bench: Evaluating Lie Detectors for Language Models](https://mlsanity.com/paper/2511.16035/) (2025)
- [The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes](https://mlsanity.com/paper/2602.15515/) (2026)
- [Preference Learning with Lie Detectors can Induce Honesty or Evasion](https://mlsanity.com/paper/2505.13787/) (2025)
- [One Probe Won't Catch Them All: Towards Targeted Deception Detection](https://mlsanity.com/paper/2602.01425/) (2026)
- [Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling](https://mlsanity.com/paper/2604.13386/) (2026)
- [Differentiable Filtering for Learning Hidden Markov Models](https://mlsanity.com/paper/2511.10571/) (2025)
- [Diverse and Adaptable Arm Coordination for Octopus-Crawling via Diffusion-Based Uncertainty-Aware Optimization](https://mlsanity.com/paper/2609.21138/) (2026)

## Abstract (arXiv)

A deception detector is only as useful as the trust its alarms deserve. Like a polygraph, detectors that read a language model's internal activations can catch deceptive responses that look honest. Yet current detectors depend on which layers they read, weaken on broader tests, and do not state how certain their alarms are. This white paper proposes the Machine Deception Detector, which targets both detection accuracy and the uncertainty of detector scores. The detector reads every layer of the language model, learns which tokens carry evidence of deception using only response labels, and calibrates its alarm threshold so that its false--positive rate stays below a prescribed level. An ensemble of such detectors measures the uncertainty of each score and raises an alarm only when its members agree, with a confidence level that sets how certain each alarm must be. The proposed evaluation trains on instructed honest and deceptive statements, tests on five unseen deceptive tasks of Liars' Bench read by six Qwen3 models from 0.6B to 32B parameters, and is designed to also show which layers carry the deception feature and how this changes with model size.