Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue

TL;DR

This paper introduces a simple, interpretable metric called semantic delta that effectively distinguishes between human and LLM-generated dialogue based on thematic concentration, showing that AI outputs tend to be more thematically rigid.

Contribution

The work presents a novel, lightweight semantic delta metric derived from Empath analysis to differentiate human and LLM dialogues, enhancing detection methods.

Findings

AI texts have higher semantic delta than human texts.

Human dialogue shows broader semantic distribution.

Semantic delta can complement existing detection techniques.

Abstract

Do LLMs talk like us? This question intrigues a multitude of scholar and it is relevant in many fields, from education to academia. This work presents an interpretable statistical feature for distinguishing human written and LLMs generated dialogue. We introduce a lightweight metric derived from semantic categories distribution. Using the Empath lexical analysis framework, each text is mapped to a set of thematic intensity scores. We define semantic delta as the difference between the two most dominant category intensities within a dialogue, hypothesizing that LLM outputs exhibit stronger thematic concentration than human discourse. To evaluate this hypothesis, conversational data were generated from multiple LLM configurations and compared against heterogeneous human corpora, including scripted dialogue, literary works, and online discussions. A Welch t-test was applied to the resulting distributions of semantic delta values. Results show that AI-generated texts consistently produce higher deltas than human texts, indicating a more rigid topics structure, whereas human dialogue displays a broader and more balanced semantic spread. Rather than replacing existing detection techniques, the proposed zero-shot metric provides a computationally inexpensive complementary signal that can be integrated into ensemble detection systems. These finding also contribute to the broader empirical understanding of LLM behavioural mimicry and suggest that thematic distribution constitutes a quantifiable dimension along which current models fall short of human conversational dynamics.