LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks

2026-04-13

AI Summary

This work addresses the cold-start problem in online advertising, where new ads lack sufficient user feedback for reliable click-through rate (CTR) prediction. The authors propose a training-free personalized CTR prediction method that leverages a large language model (LLM) as a hypernetwork to directly generate parameters of a linear CTR model from raw ad content. By integrating CLIP-based multimodal embeddings and few-shot chain-of-thought prompting, the approach dynamically produces model weights, further stabilized through weight normalization and calibration mechanisms to ensure online robustness. Experimental results demonstrate a 55.9% improvement in offline NDCG@10, and online A/B tests confirm a significantly shortened cold-start period with performance comparable to that of mature ads. The method has been successfully deployed on a leading e-commerce platform in North America.

Technology Category

• Machine Learning: Online Learning & Bandits
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

On online advertising platforms, newly introduced promotional ads face the cold-start problem, as they lack sufficient user feedback for model training. In this work, we propose LLM-HYPER, a novel framework that treats large language models (LLMs) as hypernetworks to directly generate the parameters of the click-through rate (CTR) estimator in a training-free manner. LLM-HYPER uses few-shot Chain-of-Thought prompting over multimodal ad content (text and images) to infer feature-wise model weights for a linear CTR predictor. By retrieving semantically similar past campaigns via CLIP embeddings and formatting them into prompt-based demonstrations, the LLM learns to reason about customer intent, feature influence, and content relevance. To ensure numerical stability and serviceability, we introduce normalization and calibration techniques that align the generated weights with production-ready CTR distributions. Extensive offline experiments show that LLM-HYPER significantly outperforms cold-start baselines in NDCG$@10$ by 55.9\%. Our real-world online A/B test on one of the top e-commerce platforms in the U.S. demonstrates the strong performance of LLM-HYPER, which drastically reduces the cold-start period and achieves competitive performance. LLM-HYPER has been successfully deployed in production.

Problem

• cold-start
• ad personalization
• click-through rate
• online advertising
• LLM

Innovation

• LLM-based hypernetwork
• cold-start CTR prediction
• few-shot Chain-of-Thought prompting
• multimodal ad personalization
• training-free parameter generation