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

• URL: http://arxiv.org/abs/2607.08071v1
• Date: Thu, 09 Jul 2026 02:59:04 GMT
• Title: COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation
• Abstract summary: Existing methods can generate headlines automatically and also optimize their click-through-rate (CTR) and quality.<n>We propose a novel method that uses prefix control tokens along with BART fine-tuning.<n>It yields the highest CTR and also allows users to control the length of generated headlines for use across different ad formats.
• Score: 5.768953031858987
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models [75.31791398000492]
  We develop a Unified Advertisement Generative model (Uni-AdGen) that employs a single autoregressive framework to produce both advertising images and texts.<n>To further personalize advertisements, we equip Uni-AdGen with a coarse-to-fine preference understanding module.<n>Our method outperforms baselines in general and personalized advertisement generation.
  arXiv  Detail & Related papers  (2026-05-12T13:58:06Z)
• CTR-Driven Ad Text Generation via Online Feedback Preference Optimization [28.734264007257085]
  Large Language Models (LLMs) offer efficiency advantages over manual ad text creation.<n>LLMs do not guarantee higher CTR performance compared to human-crafted texts.<n>We propose a novel ad text generation method which optimize for CTR through preference optimization from online feedback.
  arXiv  Detail & Related papers  (2025-07-27T11:13:03Z)
• CTR-Driven Advertising Image Generation with Multimodal Large Language Models [53.40005544344148]
  We explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective.<n>To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL)<n>Our method achieves state-of-the-art performance in both online and offline metrics.
  arXiv  Detail & Related papers  (2025-02-05T09:06:02Z)
• Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation [74.15447383432262]
  The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer.<n>We provide a tokenizer pre-trained on large-scale data, significantly outperforming Cosmos on zero-shot benchmarks.<n>We produce a family of auto-regressive image generation models ranging from 300M to 1.5B.
  arXiv  Detail & Related papers  (2024-09-06T17:14:53Z)
• Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction [47.7066461216227]
  Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction (E-CDCTR) Three key components: Tiny Pre-training Model (TPM), Complete Pre-training Model (CPM) and Advertisement CTR model (A-CTR) TPM provides richer representations of user and item for both the CPM and A-CTR, effectively alleviating the problem inherent in the daily updates.
  arXiv  Detail & Related papers  (2024-08-29T03:34:39Z)
• Boost CTR Prediction for New Advertisements via Modeling Visual Content [55.11267821243347]
  We exploit the visual content in ads to boost the performance of CTR prediction models. We learn the embedding for each visual ID based on the historical user-ad interactions accumulated in the past. After incorporating the visual ID embedding in the CTR prediction model of Baidu online advertising, the average CTR of ads improves by 1.46%, and the total charge increases by 1.10%.
  arXiv  Detail & Related papers  (2022-09-23T17:08:54Z)
• CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning [14.912117221662054]
  We propose CREATER, a CTR-driven advertising text generation approach, to generate ad texts based on high-quality user reviews. To incorporate CTR objective, our model learns from online A/B test data with contrastive learning, which encourages the model to generate ad texts that obtain higher CTR. Experiments on industrial datasets show that CREATER significantly outperforms current approaches.
  arXiv  Detail & Related papers  (2022-05-18T14:17:04Z)
• TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity [16.10904771281746]
  We propose an ad text strength indicator (TSI) which: (i) predicts the click-through-rate (CTR) for an input ad text, (ii) fetches similar existing ads to create a neighborhood around the input ad, and compares the predicted CTRs in the neighborhood to declare whether the input ad is strong or weak. As suggestions for ad text improvement, TSI shows anonymized versions of superior ads (higher predicted CTR) in the neighborhood.
  arXiv  Detail & Related papers  (2021-08-18T16:24:40Z)
• Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure [24.13017090236483]
  Ad creatives with enjoyable visual appearance may increase the click-through rate (CTR) of products. We propose an Adaptive and Efficient ad creative Selection framework based on a tree structure. Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.
  arXiv  Detail & Related papers  (2021-03-02T03:39:41Z)
• The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement [59.58372539336339]
  Eye-catching headlines function as the first device to trigger more clicks, bringing reciprocal effect between producers and viewers. We propose a Disentanglement-based Attractive Headline Generator (DAHG) that generates headline which captures the attractive content following the attractive style.
  arXiv  Detail & Related papers  (2020-12-14T11:11:43Z)

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.