DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning

TL;DR

DecepGPT introduces a schema-driven approach with multicultural datasets and robust multimodal learning modules to improve deception detection accuracy, interpretability, and cross-cultural generalization.

Contribution

The paper presents a new multicultural deception dataset, reasoning-augmented benchmarks, and two novel modules for robust multimodal deception detection under small-data conditions.

Findings

Achieved state-of-the-art performance on multiple benchmarks.

Demonstrated improved cross-domain and cross-cultural generalization.

Provided auditable reasoning reports for deception detection.

Abstract

Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security. In these high-stakes settings, investigators need verifiable evidence connecting audiovisual cues to final decisions, along with reliable generalization across domains and cultural contexts. However, existing benchmarks provide only binary labels without intermediate reasoning cues. Datasets are also small with limited scenario coverage, leading to shortcut learning. We address these issues through three contributions. First, we construct reasoning datasets by augmenting existing benchmarks with structured cue-level descriptions and reasoning chains, enabling model output auditable reports. Second, we release T4-Deception, a multicultural dataset based on the unified ``To Tell The Truth'' television format implemented across four countries. With 1695 samples, it is the largest non-laboratory deception detection dataset. Third, we propose two modules for robust learning under small-data conditions. Stabilized Individuality-Commonality Synergy (SICS) refines multimodal representations by synergizing learnable global priors with sample-adaptive residuals, followed by a polarity-aware adjustment that bi-directionally recalibrates representations. Distilled Modality Consistency (DMC) aligns modality-specific predictions with the fused multimodal predictions via knowledge distillation to prevent unimodal shortcut learning. Experiments on three established benchmarks and our novel dataset demonstrate that our method achieves state-of-the-art performance in both in-domain and cross-domain scenarios, while exhibiting superior transferability across diverse cultural contexts. The datasets and codes will be released.