Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.39807

Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations

Maximilian von Klinski·Sebastian Lapuschkin·Wojciech Samek·Lennart Bürger
View original source ↗Read source document ↗Export metadata ↓

Abstract

Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicates what "truth" means for an LLM: language models can adopt a wide range of personas that take very different claims to be true, including personas whose beliefs clearly contradict reality, such as a conspiracy theorist. In this work, we investigate whether lie detection probes reliably flag falsehoods generated under such an anti-factual persona or whether they instead follow the persona's beliefs. We introduce a dataset of 8,916 human-reviewed, on-policy responses from three LLMs adopting anti-factual personas. Evaluating eight probes from prior work, we find that many fail in this setting, particularly when correct and incorrect answers are evaluated under the same persona prompt. To investigate why, we construct three novel confounder datasets in which truth is anti-correlated with a potential confounding concept. Our experiments reveal that many existing probes strongly track concepts that are spuriously correlated with truth in their training data, such as instruction compliance or response likelihood. Based on these findings, we introduce a simple linear probe that achieves the strongest overall performance on both the persona and confounder stress tests. Our results suggest that current lie detection probes are far from reliable and highlight the need for training data in which truth is decorrelated from confounding concepts.

Explore related subjects

cs.CLcs.AIcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Maximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek, Lennart Bürger. 2026-09-30. Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations. https://arxiv.org/abs/2609.39807

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Post-hoc Disentanglement of Textual and Acoustic Features in Pre-trained Speech Encoders

Pre-trained speech models build entangled internal representations, which capture a variety of features (e.g., pitch, loudness, syntax, or semantics of an utterance) in a distributed encoding. This entanglement makes it difficult to track how such representations rely on textual versus acoustic information when used in downstream applications, limiting their interpretability and transparency. In this paper, we explore an approach to post-hoc disentanglement that builds on the Information Bottleneck principle. We take representations from pre-trained speech encoders as input, and separate them into two distinct components in a cascaded fashion: first we learn a vector encoding content (i.e., what can be transcribed as text), and nothing else; second, we learn a vector encoding all complementary acoustic features relevant to a target task. We apply and evaluate our proposed setup to emotion recognition and speaker identification target tasks, quantifying the relative contribution of textual and acoustic features at each model layer. Finally, we use the approach for disentangled feature attribution as it allows us to identify the most salient speech frames from both the textual and acoustic perspectives.

cs.CL↗
arXiv2026

The Super Emotion Dataset

Despite the wide-scale usage and development of emotion classification datasets in NLP, the field lacks a standardized, large-scale resource that follows a psychologically grounded taxonomy. Existing datasets either use inconsistent emotion categories, suffer from limited sample size, or focus on specific domains. The SuperEmotion dataset addresses this gap by harmonizing diverse text sources into a unified framework based on Shaver's empirically validated emotion taxonomy, enabling more consistent cross-domain emotion recognition research. This report describes version 2 of the dataset. We also report baseline results for a fine-tuned ModernBERT encoder.

cs.CL↗
arXiv2026

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

Large Language Model (LLM) agents have shown great potential in addressing real-world data science problems. LLM-driven data science agents promise to automate the entire machine learning pipeline, yet their real-world effectiveness remains limited. Existing frameworks depend on rigid, pre-defined workflows and inflexible coding strategies; consequently, they excel only on relatively simple, classical problems and fail to capture the empirical expertise that human practitioners bring to complex, innovative tasks. In this work, we introduce AutoMind, an adaptive, knowledgeable LLM-agent framework that overcomes these deficiencies through three key advances: (1) a curated expert knowledge base that grounds the agent in domain expert knowledge, (2) an agentic knowledgeable tree search algorithm that strategically explores possible solutions, and (3) a self-adaptive coding strategy that dynamically tailors code generation to task complexity. Evaluations on two automated data science benchmarks demonstrate that AutoMind delivers superior performance versus state-of-the-art baselines. Additional analyses confirm favorable effectiveness, efficiency, and qualitative solution quality, highlighting AutoMind as an efficient and robust step toward fully automated data science. Code is at https://github.com/zjunlp/AutoMind.

cs.CL↗