COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation

Researchers propose COBART, a method combining prefix control tokens with BART fine-tuning for ad headline generation, achieving a 25.82% improvement in Rouge-L and a 5.82% increase in estimated CTR over previous baselines. The approach allows users to control headline length for different ad formats and can be adapted to other architectures and optimization criteria.

arXiv:2607.08071v1 Announce Type: new Abstract: Online ads are essential to all businesses and ad headlines are one of their core creative component. Existing methods can generate headlines automatically and also optimize their click-through-rate CTR and quality. However, evolving ad formats and changing creative requirements make it difficult to generate optimized & customized headlines. We propose a novel method that uses prefix control tokens along with BART fine-tuning. It yields the highest CTR and also allows users to control the length of generated headlines for use across different ad formats. The method is also flexible and can easily be adapted to other architectures, creative requirements and optimization criteria. Our experiments demonstrate a 25.82% increment in Rouge-L and a 5.82% increment in estimated CTR over previously published strong ad headline generation baseline.