Get Started
Home
Topics
Search
Library
Research questionHow susceptible are large language models to conspiratorial responses under demographic conditioning?Large language models may reproduce elements of conspiratorial belief, while targeted prompts can shift their responses toward conspiratorial narratives. Socio-demographic conditioning may also reveal uneven biases in these responses.
AI
Alignment & Safety
Evaluation & Benchmarks
Natural Language Processing
Latest papersRecent research connected to this question, newest first.Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Tendencies in Large Language ModelsThe study examines multiple LLMs using validated psychometric surveys under different prompting and conditioning strategies, including socio-demographic attributes. Its evidence concerns partial agreement with conspiracy-related beliefs, demographic variation, and susceptibility to targeted prompting; it does not establish specific mitigation measures.research paper · Sep 4, 2026
Related questions
How can LLMs predict flexible workers’ responses to hypothetical pension policies without costly field experiments?How should LLM safety be assessed when jailbreak vulnerability varies by language and persuasive phrasing?How can bias evaluations of large language models diagnose affected groups and reasons behind biased outputs?When does an LLM’s verbal confidence reliably reflect its underlying uncertainty?