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

Yashal Shakti Kanungo, Gyanendra Das, Pooja A, Sumit Negi
7/9/2026
cs.CLcs.AIcs.LG

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Ad Headline Generation using Self-Critical Masked Language Model

83% match2026

Beyond Quality: Unlocking Diversity in Ad Headline Generation with Large Language Models

83% match2025

LLM-guided headline rewriting for clickability enhancement without clickbait

81% match2026

DeepGen: Diverse Search Ad Generation and Real-Time Customization

79% match2022

StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation

79% match1 repo22023

CTR-Driven Advertising Image Generation with Multimodal Large Language Models

78% match1 repo682025

Cite this paper

@article{kanungo2026cobart,
  title  = {COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation},
  author = {Yashal Shakti Kanungo and Gyanendra Das and Pooja A and Sumit Negi},
  year   = {2026},
  eprint = {2607.08071},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2607.08071v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2607.08071.svg)](https://codeofpaper.com/paper/2607.08071)

Discussion