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

July 09, 2026 · Grace Period · 🏛 Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22), August 14-18, 2022, Washington, DC, USA, pp. 3127-3136

Authors Yashal Shakti Kanungo, Gyanendra Das, Pooja A, Sumit Negi arXiv ID 2607.08071 Category cs.CL: Computation & Language Cross-listed cs.AI, cs.LG Citations 0 Venue Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22), August 14-18, 2022, Washington, DC, USA, pp. 3127-3136

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.