LLM-Generated Ads: From Personalization Parity to Persuasion Superiority

2025-12-03

AI Summary

Prior work lacks systematic evaluation of large language models’ (LLMs) efficacy in generating persuasive, personalized advertisements. Method: We conduct a controlled experiment assessing LLM-generated ads along two dimensions—personalization alignment (based on Big Five personality traits: openness and neuroticism) and psychological persuasion (leveraging four principles: authority, consensus, consistency, and scarcity)—and compare them against human-expert-crafted ads. Contribution/Results: LLMs significantly outperform humans in authority- and consensus-based persuasion (p < 0.01), with this advantage persisting even when users are explicitly informed of AI authorship. Overall ad preference for LLM-generated content reaches 59.1%, significantly exceeding the human baseline (40.9%). Notably, 29.4% of users actively select AI-generated ads despite full awareness—a finding that controls for potential “detection penalty.” This study provides the first empirical evidence that LLMs can achieve parity in personalization while surpassing humans in persuasive efficacy, establishing foundational theoretical and practical frameworks for AI-driven precision marketing.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

As large language models (LLMs) become increasingly capable of generating persuasive content, understanding their effectiveness across different advertising strategies becomes critical. This paper presents a two-part investigation examining LLM-generated advertising through complementary lenses: (1) personality-based and (2) psychological persuasion principles. In our first study (n=400), we tested whether LLMs could generate personalized advertisements tailored to specific personality traits (openness and neuroticism) and how their performance compared to human experts. Results showed that LLM-generated ads achieved statistical parity with human-written ads (51.1% vs. 48.9%, p>0.05), with no significant performance differences for matched personalities. Building on these insights, our second study (n=800) shifted focus from individual personalization to universal persuasion, testing LLM performance across four foundational psychological principles: authority, consensus, cognition, and scarcity. AI-generated ads significantly outperformed human-created content, achieving a 59.1% preference rate (vs. 40.9%, p<0.001), with the strongest performance in authority (63.0%) and consensus (62.5%) appeals. Qualitative analysis revealed AI's advantage stems from crafting more sophisticated, aspirational messages and achieving superior visual-narrative coherence. Critically, this quality advantage proved robust: even after applying a 21.2 percentage point detection penalty when participants correctly identified AI-origin, AI ads still outperformed human ads, and 29.4% of participants chose AI content despite knowing its origin. These findings demonstrate LLMs'evolution from parity in personalization to superiority in persuasive storytelling, with significant implications for advertising practice given LLMs'near-zero marginal cost and time requirements compared to human experts.

Problem

• Evaluates LLM effectiveness in personalized advertising based on personality traits.
• Tests LLM performance using universal psychological persuasion principles in ads.
• Compares AI-generated ads to human-created content for persuasion superiority.

Innovation

• LLMs match human experts in personalized ad creation.
• AI outperforms humans using psychological persuasion principles.
• LLMs craft sophisticated messages with visual-narrative coherence.