Paper

Steering LLM Viewpoints through Fabricated Evidence Injection

arXiv:2606.06244v1 Announce Type: new Abstract: As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cognitive vulnerability in LLMs: their tendency to uncritically trust external context when presented with fabricated evidence bearing markers of credibility. We introduce Ghostwriter, a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant quer…

Authors:

Related discussions