Line of inquiry
Inquiring lines›What do model internals reveal abo…›How do surface signals and framing…›this line of inquiry
What mechanisms enable AI systems to generate and spread false beliefs?
A broader line of inquiry — a family of 32 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 32
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- What makes experience-dependent claims categorically different from other types of fabricated statements?
- Why does false information spread faster when presupposed rather than asserted?
- Can discourse-level analysis detect deception better than individual word choices alone?
- How does cognitive load explain linguistic patterns in both deception and incorrect reasoning?
- Can representational asymmetry between self and other explain deception emergence?
- Does AI-generated text about personal experiences create a distinct category of falsity?
- How do conversation dynamics push models toward false beliefs?
- Can AI systems detect deception by monitoring real-time linguistic style matching patterns?
- Can a single fabricated claim shift model beliefs as much as multi-turn pressure?
- Do the four deception detection frameworks apply equally to AI-generated and human-intentional falsity?
- Do deception features and honesty features track the same underlying property?
- Can AI fabricate true factual claims while remaining unable to claim true experiences?
- How does linguistic style matching signal deceptive communication in human dialogue?
- How can vague language serve both cooperative and deceptive communication purposes?
- Why are false presuppositions more persuasive than false assertions?
- Why do reality monitoring accounts contain more sensory details than deceptive ones?
- How does linguistic style change when people deceive conversational AI?
- Can linguistic style matching reveal whether someone is being deceptive?
- How do partial truths and weasel words differ as deception strategies?
- How can we detect dishonesty in model outputs separate from capability failures?
- Why does truth bias prevent people from detecting multiple manipulation tactics?
- Why do suspicious listeners force deceivers to further adapt their communication style?
- Why do conspiracy beliefs persist despite counterevidence in normal settings?
- How do presuppositions exploit the logos-pathos space in explanations?
- Does reducing social judgment help both honesty and dishonesty equally?
- Why do non-factive verbs and triggers both fool language models?
- What circuit mechanisms produce belief bias in syllogistic reasoning?
- Does reducing one conspiracy belief change overall conspiratorial worldview?
- What makes counterfeiting social warrant different from counterfeiting factual claims?
- What cognitive constraints limit how complex a deception can become?
- How do false agreements emerge differently from genuine bilateral convergence?
- How do verification labels themselves become part of the misinformation problem?