Pith. sign in

REVIEW 4 cited by

Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.18249 v2 pith:EOTZLZMC submitted 2024-03-27 cs.CL cs.SI

Yanshen Sun , Jianfeng He , Limeng Cui , Shuo Lei , Chang-Tien Lu This is my paper
classification cs.CLcs.SI
keywords fakenewsvlprompthumanattackscurrentdatasetdeceptive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements in Large Language Models (LLMs) have enabled the creation of fake news, particularly in complex fields like healthcare. Studies highlight the gap in the deceptive power of LLM-generated fake news with and without human assistance, yet the potential of prompting techniques has not been fully explored. Thus, this work aims to determine whether prompting strategies can effectively narrow this gap. Current LLM-based fake news attacks require human intervention for information gathering and often miss details and fail to maintain context consistency. Therefore, to better understand threat tactics, we propose a strong fake news attack method called conditional Variational-autoencoder-Like Prompt (VLPrompt). Unlike current methods, VLPrompt eliminates the need for additional data collection while maintaining contextual coherence and preserving the intricacies of the original text. To propel future research on detecting VLPrompt attacks, we created a new dataset named VLPrompt fake news (VLPFN) containing real and fake texts. Our experiments, including various detection methods and novel human study metrics, were conducted to assess their performance on our dataset, yielding numerous findings.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs

    cs.CL 2025-08 conditional novelty 5.0 of 10

    LLM-generated jailbreak prompts elicited health misinformation from GPT-3.5, Llama 3.1-8B, and Gemini 2.0 Flash at high rates, and both LLM judges and simple classifiers detected the resulting texts with high accuracy.

  2. The Compositional Architecture of Regret in Large Language Models

    cs.CL 2025-06 reject novelty 5.0 of 10

    The paper claims that regret in LLMs is encoded by interacting neuron groups detectable in the final hidden layer, using new S-CDI, RDS, and GIC metrics.

  3. RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A new 6K-claim benchmark evaluates LLMs and multimodal LLMs on real-world fact-checking with an explicit 'unknown' option and shows web search and multimodal input improve performance.

  4. Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection

    cs.CL 2025-05 reject novelty 4.0 of 10

    A fake-news detector that spreads LLM-generated pseudo labels over a similarity graph reports state-of-the-art accuracy, but the evaluation is weakened by test-set tuning and self-label leakage at inference.

Pith tools