Line of inquiry
Inquiring lines›How does AI language shape human u…›How do language, perspective, and…›this line of inquiry
What linguistic and rhetorical features drive persuasion in language and models?
A broader line of inquiry — a family of 56 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 56
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- When does analytical persuasion work better than emotional persuasion?
- Does first-person framing change how language models assess persuasion?
- Does expressed certainty actually persuade users more than evidence?
- Do LLMs achieve similar persuasive outcomes through different rhetorical mechanisms than humans?
- Can persuasion research measure language effects without confounding them with audience composition?
- Do readers with weakly held priors respond more to linguistic features than ideologically committed ones?
- What rhetorical mechanisms drive equivalent persuasion across human and LLM arguments?
- How does persuasive framing replace evidence in contested domains?
- Does defensive friction in conversation actually protect people from persuasion?
- Why does persuasive framing replace evidence when LLM debates lack ground truth?
- What role does stylistic convergence play in LLM persuasion effectiveness?
- Why does who makes an argument matter as much as what the argument says?
- Why does showing counterarguments restore users' ability to discriminate?
- Does argument quality in textbooks differ from persuasive effectiveness in practice?
- Does cognitive complexity strengthen or weaken persuasive impact on audiences?
- Why do LLMs persuade through logical appeals but humans through emotion?
- Which linguistic features predict persuasion only after audience composition is held constant?
- Can scaling resolve the gap between LLM and human persuasion sensitivity?
- Why does LLM persuasive advantage fade across multiple interactions with users?
- Does persuasiveness increase when LLMs argue for claims that are actually true?
- Does persuasive framing substitute for evidence in contested domains?
- Can persuasion effectiveness depend on the personality of who you are trying to convince?
- Does sounding confident in framing make arguments more persuasive despite weaker logic?
- Do form, evidentiality, and tone interact with the size effect?
- Does persuasion work the same way for all personality types and contexts?
- Can LLM persuasion be fairly evaluated without stratifying by reader background?
- Why are false presuppositions more persuasive than false assertions?
- How much does reader ideology matter compared to the words being used?
- How much do LLM persuasiveness claims hide heterogeneous effects across different reader ideologies?
- Can observers detect when LLMs comprehend versus when they merely persuade?
- Can LLMs adapt persuasion strategies when they cannot track the listener's state?
- What linguistic triggers make presuppositions most persuasive to readers?
- Do moral appeals and sentiment operate on independent psychological channels?
- Does endorsement structure outperform content in detecting social controversy?
- Can LLMs ever activate the peripheral route of persuasion?
- How does social standing give certain claims more persuasive power than others?
- Does unconditional stylistic mirroring harm or help LLM persuasiveness?
- Which linguistic features predict persuasion once reader ideology is statistically controlled?
- Can formal argumentation structure replace ad-hoc fallacy classifications?
- Why does renaming the entity change how compelling the argument feels?
- Can factually accurate summaries persuade readers without sacrificing accuracy?
- What makes an argument fallacious according to formal linguistic criteria?
- Why does personal authenticity matter more for human persuasion than LLM?
- Why do conspiracy beliefs persist despite counterevidence in normal settings?
- How do fallacy susceptibilities relate to LLM persuasiveness in debates?
- How do presuppositions exploit the logos-pathos space in explanations?
- How does evaluative stance differ from structural argument analysis?
- Does GenAI use different persuasion tactics for different professional audiences or expertise levels?
- Why do aggregate persuasion metrics mask what actually changes minds?
- Can we measure sophistry by tracking conviction density in model outputs?
- Does the type of validation trigger different persuasion strategies in GPT-4?
- How does the first-order and second-order distinction unify classical and modern argument theory?
- How do internal and external topoi differ in classical rhetoric?
- How do ethical persuasion strategies differ from unethical jailbreak techniques?
- What are the nine possible proposition-type combinations in arguments?
- What are the three orthogonal axes that structure the argument scheme periodic table?