Can Deception Detection Go Deeper? Dataset, Evaluation, and Benchmark for Deception Reasoning

TL;DR

This paper introduces a new deception reasoning task that extends traditional deception detection by providing objective evidence and analyzing the intent behind potential lies, aiming to improve real-world applicability and evaluate large language models.

Contribution

It presents a novel deception reasoning task, constructs a dataset, defines evaluation metrics, and establishes a benchmark for reasoning capabilities of large language models.

Findings

Constructed a new deception reasoning dataset

Defined evaluation metrics for deception reasoning

Serves as a benchmark for large language models' reasoning

Abstract

Deception detection has attracted increasing attention due to its importance in real-world scenarios. Its main goal is to detect deceptive behaviors from multimodal clues such as gestures, facial expressions, prosody, etc. However, these bases are usually subjective and related to personal habits. Therefore, we extend deception detection to deception reasoning, further providing objective evidence to support subjective judgment. Specifically, we provide potential lies and basic facts and then analyze why this sentence may be a lie by combining factual inconsistencies and intent behind them. Compared with deception detection, this task is more applicable to real-world scenarios. For example, in interrogation, the police should judge whether a person is lying based on solid evidence. This paper presents our initial attempts at this task, including constructing a dataset and defining evaluation metrics. Meanwhile, this task can serve as a benchmark for evaluating the complex reasoning capability of large language models. Our code and data are provided in the supplementary material.