Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915882299555840 |
|---|---|
| author | Wang, Chi Gao, Min Wang, Zongwei Yin, Junwei Shu, Kai Lin, Chenghua |
| author_facet | Wang, Chi Gao, Min Wang, Zongwei Yin, Junwei Shu, Kai Lin, Chenghua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12632 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection Wang, Chi Gao, Min Wang, Zongwei Yin, Junwei Shu, Kai Lin, Chenghua Computation and Language 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. |
| title | Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.12632 |