Paper
Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
Authors
Wenwei Li, Ming Xu, Tianle Xia, Lingxiang Hu, Yiding Sun, Linfang Shang, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang
Abstract
Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it in production remains challenging because industrial knowledge is inherently relational, frequently updated, and insufficiently aligned with generation objectives. We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for multi-hop, domain-specific evidence selection; and (2) evidence-constrained reinforcement learning via Group Relative Policy Optimization (GRPO) with multi-dimensional rewards covering faithfulness, style compliance, safety, and URL validity. Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety, while reducing the hallucination rate by 72\%. A two-week online A/B test demonstrates a 28.6\% increase in like rate, a 46.2\% decrease in dislike rate, and a 92.7\% reduction in URL hallucination. The system has been running in production for over half a year and has served millions of QA interactions.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.22584v1</id>\n <title>Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA</title>\n <updated>2026-02-26T03:35:09Z</updated>\n <link href='https://arxiv.org/abs/2602.22584v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.22584v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it in production remains challenging because industrial knowledge is inherently relational, frequently updated, and insufficiently aligned with generation objectives. We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for multi-hop, domain-specific evidence selection; and (2) evidence-constrained reinforcement learning via Group Relative Policy Optimization (GRPO) with multi-dimensional rewards covering faithfulness, style compliance, safety, and URL validity. Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety, while reducing the hallucination rate by 72\\%. A two-week online A/B test demonstrates a 28.6\\% increase in like rate, a 46.2\\% decrease in dislike rate, and a 92.7\\% reduction in URL hallucination. The system has been running in production for over half a year and has served millions of QA interactions.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <published>2026-02-26T03:35:09Z</published>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Wenwei Li</name>\n </author>\n <author>\n <name>Ming Xu</name>\n </author>\n <author>\n <name>Tianle Xia</name>\n </author>\n <author>\n <name>Lingxiang Hu</name>\n </author>\n <author>\n <name>Yiding Sun</name>\n </author>\n <author>\n <name>Linfang Shang</name>\n </author>\n <author>\n <name>Liqun Liu</name>\n </author>\n <author>\n <name>Peng Shu</name>\n </author>\n <author>\n <name>Huan Yu</name>\n </author>\n <author>\n <name>Jie Jiang</name>\n </author>\n </entry>"
}