arXiv cs.CL· Riccardo Loconte, Jonas Festor, Zane Fatjanova, Mariam Bolkvadze, Bennett Kleinberg·· 9 天前AI 评分39
自动语言欺骗检测存在持续准确率天花板
A persistent accuracy ceiling in automated verbal deception detection
AI 导读
一项系统综述与元分析发现，自动语言欺骗检测的汇总准确率为 74.4%（95% CI：71.2%-77.4%），与人工方法相当，暗示 70-75% 的准确率天花板。
正文 · 原文
Abstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.12118 [cs.CL] |
| (or arXiv:2610.12118v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12118 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Riccardo Loconte [view email]
[v1]
Thu, 8 Oct 2026 15:15:32 UTC (3,238 KB)
来源：arXiv cs.CL · arxiv.org