Does linguistic conviction explain why LLMs persuade more effectively?
Research investigates whether LLMs' persuasive advantage stems from expressing higher linguistic certainty than humans, and whether this confidence-loading effect operates independently of factual accuracy.
Schoenegger's linguistic analysis of persuader texts produces a clean candidate mechanism for the LLM persuasive edge: models express higher conviction than human persuaders, and conviction-loading correlates with persuasive advantage. Confidence is the lever, and crucially it is generated regardless of truth value. This explains why the same model is equally good at pushing toward right and wrong answers — what does the work is the register, not the substrate.
This sharpens Does RLHF training make models more convincing or more correct? from causal claim to behavioral signature. RLHF post-training installs assertive register as default — minimal hedging, minimal explicit uncertainty quantification, declarative cadence — because that register reads as "helpful" to raters more often than hedged variants. The result is a model whose factual content can be wrong while its rhetorical surface remains certain. Schoenegger gives a measurable footprint of this register and ties it directly to persuasive outcomes.
The connection to llms are susceptible to logical fallacies 41 to 69 percent more often than humans — revealing that reasoning robustness fails under adversarial framing is dual. LLMs are more susceptible to fallacies under adversarial framing — and more able to deploy confident-sounding fallacies persuasively against others. The defensive and offensive deficits are linked: a system without robust uncertainty calibration both falls for confident bullshit and produces it.
The content-independence of the conviction lever is the load-bearing finding. If high conviction increased persuasive impact only on true claims, this would be a feature, not a bug. The fact that it works equally on false claims means RLHF is installing a content-independent persuasion amplifier. Every deployment that raises persuasiveness through these techniques raises it for both truthful and deceptive uses, in proportion.
For writing about AI rhetoric, the operational handle: the diagnostic for sophistry is not surface fluency but conviction-density per claim. A response with high confidence-loading and low explicit uncertainty quantification is a sophistry candidate regardless of whether its conclusions happen to be correct.
Inquiring lines that read this note 43
This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.
How does persona conditioning amplify demographic stereotyping and bias in models? Do writers recognize when AI writing assistance alters their expressed stance? What factors drive AI persuasiveness and how can it be mitigated?- Does persuasiveness increase when LLMs argue for claims that are actually true?
- Why do different model families show opposite persuasion strengths?
- How do fallacy susceptibilities relate to LLM persuasiveness in debates?
- How does source attribution change the complexity-persuasion relationship?
- Does cognitive complexity strengthen or weaken persuasive impact on audiences?
- Why does LLM persuasive advantage fade across multiple interactions with users?
- Does defensive friction in conversation actually protect people from persuasion?
- Does training for persuasiveness harm a model's factual accuracy?
- Can post-training techniques create persuasive advantage where none existed?
- What rhetorical mechanisms drive equivalent persuasion across human and LLM arguments?
- Does argument quality in textbooks differ from persuasive effectiveness in practice?
- Do LLMs achieve similar persuasive outcomes through different rhetorical mechanisms than humans?
- Does unconditional stylistic mirroring harm or help LLM persuasiveness?
- How does post-training persuasion ability interact with exposure-based decay over time?
- What role does stylistic convergence play in LLM persuasion effectiveness?
- Can post-training methods that increase persuasiveness also decrease factual accuracy?
- Can persuasion research measure language effects without confounding them with audience composition?
- Which linguistic features predict persuasion once reader ideology is statistically controlled?
- How much do LLM persuasiveness claims hide heterogeneous effects across different reader ideologies?
- When does analytical persuasion work better than emotional persuasion?
- Which linguistic features predict persuasion only after audience composition is held constant?
- Does expressed certainty actually persuade users more than evidence?
- Does sounding confident in framing make arguments more persuasive despite weaker logic?
- Do form, evidentiality, and tone interact with the size effect?
- Can observers detect when LLMs comprehend versus when they merely persuade?
- Can LLM persuasion be fairly evaluated without stratifying by reader background?
- Why do LLMs use more moral language than humans in argumentation?
- How does personality priming change LLM strategic decision making?
- Why does personal authenticity matter more for human persuasion than LLM?
- Why do LLMs persuade through logical appeals but humans through emotion?
- Can LLMs ever activate the peripheral route of persuasion?
- How do emotional appeals affect LLM judgments versus human belief change?
- Do LLMs and humans use different routes to become persuaded?
- Why are false presuppositions more persuasive than false assertions?
- What linguistic triggers make presuppositions most persuasive to readers?
- How does social standing give certain claims more persuasive power than others?
Related concepts in this collection 2
This note in its neighbourhood — explore the map, then jump to a related concept in the list below.
Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph
-
Does RLHF training make models more convincing or more correct?
Explores whether RLHF improves actual task performance or merely trains models to sound more persuasive to human evaluators. This matters because alignment techniques could be creating the illusion of safety.
this gives the behavioral signature for the RLHF-sophistry mechanism
-
Why do LLMs accept logical fallacies more than humans?
LLMs fall for persuasive but invalid arguments at much higher rates than humans. This explores whether reasoning models genuinely evaluate logic or simply mimic argument structure.
paired offensive/defensive failure modes around uncertainty calibration
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments
- Evaluating the Capabilities of LLMs for Persuasive Dialogue
- Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments
- A meta-analysis of the persuasive power of large language models
- Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations
- When Large Language Models are More Persuasive Than Incentivized Humans, and Why
- Exploring the Role of Prior Beliefs for Argument Persuasion
- Debating with More Persuasive LLMs Leads to More Truthful Answers
Original note title
LLM persuasive advantage is mediated by linguistically expressed conviction — the model sounds more sure than the human and certainty is the lever