Theory-Guided Deception Detection: A RAG-Based Artificial Intelligence Exploration

2026-08-09

AI Summary

This study addresses the need for greater theoretical coherence and reduced judgment bias in AI-based deception detection. We propose a theory-guided reasoning model by systematically integrating seven prominent deception theories into a retrieval-augmented generation (RAG) framework. The model’s performance is evaluated against baseline large language models—including GPT-4o, Claude-Sonnet-4-6, Llama3, and DeepSeek-V4-Flash—on a dataset of 700 real-world statements. Results show that the RAG model achieves comparable accuracy (~54.5%) to the baselines while exhibiting slightly lower truth bias. Crucially, the choice of deception theory significantly influences the model’s response bias, which varies between 32.2% and 88.1%, underscoring the pivotal role of theoretical perspective in shaping AI judgments about deception.

Abstract

The current work developed seven Retrieval-Augmented Generation (RAG) models based on leading deception theories and compared how deception judgments were made relative to baseline models. Across 700 statements drawn from five published deception datasets, four large language models (gpt-4o, claude-sonnet-4-6, ollama/llama3, deepseek-v4-flash), and two run-types (RAG vs. baseline), a total of 39,200 deception judgments were rendered. Detection accuracies were consistent with typical human accuracies and not statistically different across RAG (54.5%) and baseline models (54.6%). RAG-based models (57.0%) were less truth-biased than baseline models (59.7%), but the effect size was quite small. Theoretical perspective mattered little for accuracy yet mattered substantially for response bias, which ranged from highly lie-biased (the verifiability approach, 32.2%) to highly truth-biased (truth-default theory, 88.1%). Content effects and model effects further moderated the results. Theory-guided AI judgments are unreliable with current parameters, yet they might show promise with additional datasets, model testing, and theory-to-data matching.

Problem

• deception detection
• Retrieval-Augmented Generation
• theory-guided AI
• response bias
• large language models

Innovation

• Theory-Guided AI
• Deception Detection
• Retrieval-Augmented Generation (RAG)
• Response Bias
• Large Language Models