Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA

• URL: http://arxiv.org/abs/2602.22584v1
• Date: Thu, 26 Feb 2026 03:35:09 GMT
• Title: Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
• Abstract summary: Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content can lead to financial loss, compliance violations, and legal risk.<n>We propose a reinforced co-adaptation framework that jointly optimize retrieval and generation through two components.<n> Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety.<n>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.
• Score: 11.136092421166097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Graph-Augmented Retrieval for Cross-Entity Financial Sentiment Analysis: A Comparative Study [0.0]
  This paper presents a novel two-hop Graph-RAG architecture versus a standard vector-only baseline for cross-entity financial sentiment analysis.<n>Our system constructs a sentiment-weighted knowledge graph of 59 equity entities from 255 news articles covering major technology stocks, then augments dense retrieval with intensity-filtered graph over INFLUENCES edges.
  arXiv  Detail & Related papers  (2026-05-19T18:55:15Z)
• URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models [35.441039437111606]
  URAG is a benchmark designed to assess the uncertainty of RAG systems across various fields like healthcare, programming, science, math, and general text.<n>We apply the evaluation pipeline to 8 standard RAG methods, measuring their performance through both accuracy and prediction-set sizes based on LAC and APS metrics.
  arXiv  Detail & Related papers  (2026-03-02T00:22:06Z)
• JARVIS: An Evidence-Grounded Retrieval System for Interpretable Deceptive Reviews Adjudication [4.797952842010917]
  JARVIS is a framework providing Judgment via Augmented Retrieval and eVIdence graph Structures.<n>It retrieves semantically similar evidence via hybrid dense-sparse multimodal retrieval, expands relational signals through shared entities, and constructs a heterogeneous evidence graph.<n>Our framework achieves a 27% increase in the recall volume and reduces manual inspection time by 75%.
  arXiv  Detail & Related papers  (2026-02-13T13:57:45Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems [14.028345839891855]
  Retrieval-augmented generation (RAG) systems integrate document retrieval with large language models.<n>RAG introduces a new privacy risk: adversaries can issue carefully crafted queries to exfiltrate sensitive content gradually.<n>We introduce RAGCRAWLER, which builds a knowledge graph to represent revealed information, and plans queries in semantic space that target unretrieved regions.
  arXiv  Detail & Related papers  (2026-01-22T05:59:42Z)
• Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models [48.65910216527897]
  Generation-Augmented Generation (GAG) treats private expertise as an additional expert modality and injects it via a compact representation-level interface.<n>GAG improves specialist performance over strong RAG baselines by 15.34% and 14.86% on two benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T04:23:36Z)
• L-RAG: Balancing Context and Retrieval with Entropy-Based Lazy Loading [0.0]
  Reval-Augmented Generation (RAG) has emerged as the predominant paradigm for grounding Large Language outputs in factual knowledge.<n>We introduce L-RAG, an adaptive framework that implements hierarchical context management through entropy gating.<n>L-RAG offers a practical, training-free approach toward more efficient RAG deployment.
  arXiv  Detail & Related papers  (2026-01-10T12:25:19Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes [39.61443457073034]
  We introduce EviNote-RAG, a framework that follows a retrieve-note-answer workflow.<n>Instead of reasoning directly over raw external information, the model first produces Supportive-Evidence Notes.<n>EviNote-RAG achieves state-of-the-art performance, improving answer accuracy, training stability, robustness, and efficiency.
  arXiv  Detail & Related papers  (2025-08-31T14:44:45Z)
• ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry [17.291995915394097]
  ComRAG is a retrieval-augmented generation framework for real-time industrial CQA.<n>It integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism designed for retrieval, generation, and efficient storage.
  arXiv  Detail & Related papers  (2025-06-26T08:48:16Z)
• Information Retrieval Induced Safety Degradation in AI Agents [52.15553901577888]
  This study investigates how expanding retrieval access affects model reliability, bias propagation, and harmful content generation.<n>Retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval.<n>These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems.
  arXiv  Detail & Related papers  (2025-05-20T11:21:40Z)
• DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented Generation [4.113142669523488]
  Domain-specific QA systems require generative fluency but high factual accuracy grounded in structured expert knowledge.<n>We propose DO-RAG, a scalable and customizable hybrid QA framework that integrates multi-level knowledge graph construction with semantic vector retrieval.
  arXiv  Detail & Related papers  (2025-05-17T06:40:17Z)
• T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks [67.91652526657599]
  We formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called T2V-OptJail.<n>We conduct large-scale experiments on several T2V models, covering both open-source models and real commercial closed-source models.<n>The proposed method improves 11.4% and 10.0% over the existing state-of-the-art method in terms of attack success rate.
  arXiv  Detail & Related papers  (2025-05-10T16:04:52Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG [65.0423152595537]
  We propose MES-RAG, which enhances entity-specific query handling and provides accurate, secure, and consistent responses.<n>MES-RAG introduces proactive security measures that ensure system integrity by applying protections prior to data access.<n> Experimental results demonstrate that MES-RAG significantly improves both accuracy and recall, highlighting its effectiveness in advancing the security and utility of question-answering.
  arXiv  Detail & Related papers  (2025-03-17T08:09:42Z)

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.