LLM-Generated Ads: From Personalization Parity to Persuasion Superiority

• URL: http://arxiv.org/abs/2512.03373v1
• Date: Wed, 03 Dec 2025 02:13:38 GMT
• Title: LLM-Generated Ads: From Personalization Parity to Persuasion Superiority
• Abstract summary: This paper presents a two-part investigation of large language models (LLMs)generated advertising through complementary lenses.<n>In our first study, we tested whether LLMs could generate personalized advertisements tailored to specific personality traits.<n>In our second study, we shifted focus from individual personalization to universal persuasion testing.
• Score: 14.811340973986859
• License: http://creativecommons.org/publicdomain/zero/1.0/
• 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.

Related papers

• LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions [67.08243073804717]
  We characterize how people are turning to LLMs as oracles: all-knowing authorities on subjective personal questions.<n>Motivated by risks to users' autonomy and well-being, we develop a typology and methods to measure this form of AI reliance at scale.
  arXiv  Detail & Related papers  (2026-09-13T23:47:13Z)
• Towards Personalized Federated Learning for Dysarthric Speech Recognition [49.291957451546914]
  This paper explores two aggregation strategies to achieve personalization, including the parameter-based averaging strategy and the embedding-based averaging strategy.<n> Experiments on UASpeech and TORGO show that the proposed methods outperform the baseline regularized FedAvg by statistically significant WER reductions of up to 0.99% absolute (3.15% relative) on UASpeech and 0.56% absolute (4.73% relative) on TORGO, respectively.
  arXiv  Detail & Related papers  (2026-06-11T12:10:57Z)
• Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People [81.63702981397408]
  Given limited resources, to what extent do agents based on language models (LMs) act rationally?<n>We develop methods to benchmark and enhance agentic information-seeking, drawing on insights from human behavior.<n>For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling)
  arXiv  Detail & Related papers  (2025-10-23T17:57:28Z)
• What Makes a Good Natural Language Prompt? [72.3282960118995]
  We conduct a meta-analysis surveying more than 150 prompting-related papers from leading NLP and AI conferences from 2022 to 2025.<n>We propose a property- and human-centric framework for evaluating prompt quality, encompassing 21 properties categorized into six dimensions.<n>We then empirically explore multi-property prompt enhancements in reasoning tasks, observing that single-property enhancements often have the greatest impact.
  arXiv  Detail & Related papers  (2025-06-07T23:19:27Z)
• Affordance Benchmark for MLLMs [38.62884479364572]
  We introduce **A4Bench**, a novel benchmark designed to evaluate the affordance perception abilities of MLLMs across two dimensions.<n>We evaluate 17 MLLMs (nine proprietary and eight open-source) and compare them to human performance.<n>Results show that proprietary models generally outperform open-source ones, yet all models perform far below humans.
  arXiv  Detail & Related papers  (2025-06-01T08:26:34Z)
• Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs [17.44511150123112]
  Large Language Models (LLMs) have shown significant limitations in understanding creative content.<n>We revisit this challenge by decomposing humor understanding into three components and systematically improve each.<n>Our refined approach achieves 82.4% accuracy in caption ranking, singificantly improving upon the previous 67% benchmark.
  arXiv  Detail & Related papers  (2025-02-27T18:29:09Z)
• Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages [51.96666324242191]
  We analyze whether user utilization of novel writing assistants in a charity advertisement writing task is affected by the AI's performance in a second language.<n>We quantify the extent to which these patterns translate into the persuasiveness of generated charity advertisements.
  arXiv  Detail & Related papers  (2025-02-13T17:49:30Z)
• Human Decision-making is Susceptible to AI-driven Manipulation [87.24007555151452]
  AI systems may exploit users' cognitive biases and emotional vulnerabilities to steer them toward harmful outcomes.<n>This study examined human susceptibility to such manipulation in financial and emotional decision-making contexts.
  arXiv  Detail & Related papers  (2025-02-11T15:56:22Z)
• Persuasion with Large Language Models: a Survey [49.86930318312291]
  Large Language Models (LLMs) have created new disruptive possibilities for persuasive communication. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks.
  arXiv  Detail & Related papers  (2024-11-11T10:05:52Z)
• Can Language Models Recognize Convincing Arguments? [12.458437450959416]
  Large language models (LLMs) have raised concerns about their potential to create and propagate convincing narratives. We study their performance in detecting convincing arguments to gain insights into their persuasive capabilities.
  arXiv  Detail & Related papers  (2024-03-31T17:38:33Z)
• On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial [10.770999939834985]
  We analyze the effect of AI-driven persuasion in a controlled, harmless setting. We found that participants who debated GPT-4 with access to their personal information had 81.7% higher odds of increased agreement with their opponents compared to participants who debated humans.
  arXiv  Detail & Related papers  (2024-03-21T13:14:40Z)
• Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision [84.31474052176343]
  Recent AI-assistant agents, such as ChatGPT, rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback to align the output with human intentions. This dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision. We propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision.
  arXiv  Detail & Related papers  (2023-05-04T17:59:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.