Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection

TL;DR

This paper introduces a novel method called LIFE that detects fake news generated by large language models by analyzing prompt-induced linguistic fingerprints, achieving state-of-the-art accuracy.

Contribution

The paper presents a new approach that uncovers and leverages prompt-induced linguistic fingerprints for more reliable detection of LLM-generated fake news.

Findings

LIFE achieves state-of-the-art detection performance.

LIFE maintains high accuracy on human-written fake news.

Key-fragment techniques enhance detection reliability.

Abstract

With the rapid development of large language models, the generation of fake news has become increasingly effortless, posing a growing societal threat and underscoring the urgent need for reliable detection methods. Early efforts to identify LLM-generated fake news have predominantly focused on the textual content itself; however, because much of that content may appear coherent and factually consistent, the subtle traces of falsification are often difficult to uncover. Through distributional divergence analysis, we uncover prompt-induced linguistic fingerprints: statistically distinct probability shifts between LLM-generated real and fake news when maliciously prompted. Based on this insight, we propose a novel method named Linguistic Fingerprints Extraction (LIFE). By reconstructing word-level probability distributions, LIFE can find discriminative patterns that facilitate the detection of LLM-generated fake news. To further amplify these fingerprint patterns, we also leverage key-fragment techniques that accentuate subtle linguistic differences, thereby improving detection reliability. Our experiments show that LIFE achieves state-of-the-art performance in LLM-generated fake news and maintains high performance in human-written fake news. The code and data are available at https://anonymous.4open.science/r/LIFE-E86A.