# A persistent accuracy ceiling in automated verbal deception detection

arXiv: https://arxiv.org/abs/2610.12118 · HTML: https://mlsanity.com/paper/2610.12118/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 110 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Open Source Software for Efficient and Transparent Reviews](https://mlsanity.com/paper/2006.12166/) (2020)
- [Pre-registration for Predictive Modeling](https://mlsanity.com/paper/2311.18807/) (2023)
- [The Mafiascum Dataset: A Large Text Corpus for Deception Detection](https://mlsanity.com/paper/1811.07851/) (2018)
- [Spam Review Detection Using Deep Learning](https://mlsanity.com/paper/2211.01675/) (2022)
- [Deception detection in text and its relation to the cultural dimension of individualism/collectivism](https://mlsanity.com/paper/2105.12530/) (2021)
- [Confounds and Overestimations in Fake Review Detection: Experimentally Controlling for Product-Ownership and Data-Origin](https://mlsanity.com/paper/2110.15130/) (2021)
- [Unmasking Falsehoods in Reviews: An Exploration of NLP Techniques](https://mlsanity.com/paper/2307.10617/) (2023)
- [When lies are mostly truthful: automated verbal deception detection for embedded lies](https://mlsanity.com/paper/2501.07217/) (2025)
- [What if Deception Cannot be Detected? A Cross-Linguistic Study on the Limits of Deception Detection from Text](https://mlsanity.com/paper/2505.13147/) (2025)
- [Humans incorrectly reject confident accusatory AI judgments](https://mlsanity.com/paper/2512.02848/) (2025)

## Abstract (arXiv)

Automated methods have been proposed to overcome the limitations of human verbal deception detection, but evidence remains fragmented across disciplines. We systematically reviewed 25 years of research (289 reports, 6,136 classification models) and meta-analyzed 3,653 models nested within 97 datasets. Pooled accuracy was 74.4% (95% CI: 71.2%-77.4%) with substantial heterogeneity. Accuracy was driven by methodological quality (ground truth, data source, class balance, evaluation procedure) more than by model complexity: the adoption of embeddings and large language models has not translated into improved predictive performance. Only 12.46% of reports used data with verifiable ground-truth, and only 23.96% of models were evaluated on independent data. The pooled accuracy aligns with meta-analyses of manual approaches, suggesting a ceiling of 70-75%, unlikely to be lifted by current research conventions.