← Back to all news
arXiv Computation and Language By Tong Guo, Teng Ye, Yutong Xie, Qiaozhu Mei

A misinformation playbook sharpens judgement without breeding cynicism

Read the original on arXiv Computation and Language →

The paper presents a defence against misinformation that focuses on the recurring persuasion strategies—social influence, information manipulation, emotional appeals, fear, conspiracy, and fabrication—rather than on fact-checking individual claims. By training people and language models on a large playbook derived from 214,646 fact-checked claims in 51 languages, the authors show that this approach can improve judgement of unfamiliar claims without increasing cynicism toward true claims. The study includes a pre-registered experiment where briefing participants with the playbook enhanced their discernment of unfamiliar claims while leaving belief in true claims unchanged, though the overall gain was not statistically significant.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Oct 9

Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

The paper presents a white‑box deception detection system that uses probes trained on the largest deception dataset (FIBS) and a novel architecture aggregating across layers and tokens. The probes achieve 98.8% AUC on SHADE‑Arena, outperforming a text‑monitoring baseline, and reach up to 99.7% AUC when detecting introspective deception that cannot be inferred from context alone. They also effectively detect deception in open‑weight models on politically sensitive topics and when models are pressured about their beliefs.

By Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba, Adam Gleave, Chris Cundy
llmsagents
More like this →
arXiv AI
Oct 5

Misinformation Without Triggers: From Factual Answers to Downstream Decisions

The study investigates how false content in training data can influence language models’ downstream decisions even without explicit triggers. By comparing models trained on misleading versus truthful documents in a controlled decision task and a real‑world bushfire case, the authors find a gap between factual answers and the decisions derived from them: correct facts do not always lead to correct decisions, and removing an injected number does not eliminate the misleading narrative. The research highlights that data poisoning can subtly alter model behavior beyond what is detectable through direct probing.

By Lin Tian, Marian-Andrei Rizoiu
llms
More like this →