The Flow has not summarised this story yet — read it at arXiv Computation and Language.
SharP is a text‑generation framework that uses both hard and soft prompts to guide large language models in creating task‑specific synthetic news samples for low‑resource fake news detection. The method combines structured factual constraints with learned semantic patterns, and employs a boundary‑aware strategy that focuses on classifier‑uncertain areas to refine decision boundaries. Dual objective optimization balances semantic alignment with source data and classifier feedback, aiming to improve robustness and generalization when labeled data are scarce.
arXiv:2606. 04199v1 Announce Type: cross Abstract: The increasing use of large language models has raised concerns about the spread of AI-generated fake news, particularly under varying prompting strategies.
FakeSpotter is a new tool that estimates the viral misinformation risk of textual content by measuring structural fingerprints of misinformation instead of directly judging truthfulness. It operates across linguistic, narrative, logical, and critical‑thinking dimensions, using repeated large language model assessments and domain‑specific logistic regression classifiers for both short and long texts. In a labeled corpus of 764 texts, FakeSpotter achieved macro F1 scores of 0.788 for short texts and 0.793 for long texts, and its interpretive layer offers explainable outputs such as feature‑based scores, signal agreement, and a caution index for social listening.
The paper "Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems" updates the 2024 survey on generative AI and misinformation, shifting from a literature review to practical countermeasures. It documents changes in the threat landscape, noting that Large Language Models and multimodal systems have improved AI-generated content, thereby worsening information quality. The authors introduce JudgeGPT, a platform for assessing human perception of AI-generated news, and RogueGPT, a controlled stimulus generation engine, forming an experimental pipeline to study detection and mitigation strategies, including LLM-based detection and inoculation approaches.
The paper addresses fake news detection when articles are rewritten with different emotional tones while keeping factual claims unchanged. The authors create emotion‑rewritten test sets and generate explanations from original articles to serve as stable background knowledge. They propose a Gated Cross Attention (GCA) framework that integrates rewritten news with explanations, improving detection performance on PolitiFact and LUN datasets and remaining competitive on GossipCop.
arXiv:2608. 15746v1 Announce Type: new Abstract: We present a forensic analysis of the generation pipeline behind a recent AI-driven influence campaign.