RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation

• URL: http://arxiv.org/abs/2602.11780v1
• Date: Thu, 12 Feb 2026 10:00:55 GMT
• Title: RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation
• Authors: Jinfang Wang, Jiajie Liu, Jianwei Wu, Ziqin Luo, Zhen Chen, Chunlei Li, Biao Han, Tao Deng, Yi Li, Shuanglong Li, Lin Liu,
• Abstract summary: In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value.<n>We propose RELATE, a reinforcement learning-based end-to-end framework that unifies generation and objective alignment within a single model.<n>To better capture ultimate advertiser value beyond click-level signals, We incorporate conversion-oriented metrics into the objective and jointly model them with compliance constraints as multi-dimensional rewards.
• Score: 17.34586562700226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value. Existing industrial systems typically follow a two-stage paradigm, where candidate texts are first generated and subsequently aligned with online performance metrics such as click-through rate(CTR). This separation often leads to misaligned optimization objectives and low funnel efficiency, limiting global optimality. To address these limitations, we propose RELATE, a reinforcement learning-based end-to-end framework that unifies generation and objective alignment within a single model. Instead of decoupling text generation from downstream metric alignment, RELATE integrates performance and compliance objectives directly into the generation process via policy learning. To better capture ultimate advertiser value beyond click-level signals, We incorporate conversion-oriented metrics into the objective and jointly model them with compliance constraints as multi-dimensional rewards, enabling the model to generate high-quality ad texts that improve conversion performance under policy constraints. Extensive experiments on large-scale industrial datasets demonstrate that RELATE consistently outperforms baselines. Furthermore, online deployment on a production advertising platform yields statistically significant improvements in click-through conversion rate(CTCVR) under strict policy constraints, validating the robustness and real-world effectiveness of the proposed framework.

Related papers

• FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation [75.50721642765994]
  Large language model (LLM)-based recommendation models have demonstrated impressive performance.<n>We propose an LLM-based framework for Federated cross-domain recommendation, FeDecider.<n>Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider.
  arXiv  Detail & Related papers  (2026-02-17T21:42:28Z)
• DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs [21.30516760599435]
  Large Language Models offer a promising alternative for AIGB.<n>They lack the numerical precision required for fine-grained optimization.<n>We propose DARA, a novel dual-phase framework that decomposes the decision-making process into two stages.<n>Our approach consistently outperforms existing baselines in terms of cumulative advertiser value under budget constraints.
  arXiv  Detail & Related papers  (2026-01-21T06:58:44Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization [51.27959658504722]
  Multi-task learning offers a principled framework to train these tasks jointly through shared representations.<n>Existing multi-task optimization strategies are primarily guided by training dynamics and often generalize poorly in volatile bidding environments.<n>We present Validation-Aligned Multi-task Optimization (VAMO), which adaptively assigns task weights based on the alignment between per-task training gradients and a held-out validation gradient.
  arXiv  Detail & Related papers  (2025-10-09T03:59:51Z)
• 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)
• RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 [20.92548890511589]
  This paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs)<n> RecLLM-R1 significantly surpasses existing baseline methods across a spectrum of evaluation metrics, including accuracy, diversity, and novelty.
  arXiv  Detail & Related papers  (2025-06-24T01:39:34Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Unified Language-driven Zero-shot Domain Adaptation [55.64088594551629]
  Unified Language-driven Zero-shot Domain Adaptation (ULDA) is a novel task setting. It enables a single model to adapt to diverse target domains without explicit domain-ID knowledge.
  arXiv  Detail & Related papers  (2024-04-10T16:44:11Z)
• 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)
• A Regularized Implicit Policy for Offline Reinforcement Learning [54.7427227775581]
  offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. We propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. Experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.
  arXiv  Detail & Related papers  (2022-02-19T20:22:04Z)
• SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
  We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
  arXiv  Detail & Related papers  (2021-01-02T01:15:57Z)

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.