用大模型检测搜索结果是否偏离用户意图，提升内容安全与体验。
Content Moderation in TV Search: Balancing Policy Compliance, Relevance, and User Experience
- 通过LLM识别用户无意中被召回的不相关或不当内容。
- 发现并标记高风险结果，反馈至初始检索系统优化。
- 适合关注搜索质量与合规性的平台产品团队参考。
数百万用户依赖娱乐平台的搜索功能发现和探索内容。现代搜索系统结合候选生成与排序策略，采用深度学习和基于大语言模型（LLM）的技术来检索、生成和分类搜索结果。尽管有这些进展，由于模型不可预测性、元数据错误或设计疏漏，搜索算法仍可能呈现不当或不相关的内容。这会偏离产品目标与用户期望，损害用户信任及业务成果。本文提出在现有流程外增加一层基于大语言模型（LLM）的监控机制，用于识别用户未意图搜索的内容。该机制作为产品品质保障基线，收集反馈以改进初始检索系统的性能，确保更安全、可靠的用户体验。
原文摘要 · Abstract (English)
Millions of people rely on search functionality to find and explore content on entertainment platforms. Modern search systems use a combination of candidate generation and ranking approaches, with advanced methods leveraging deep learning and LLM-based techniques to retrieve, generate, and categorize search results. Despite these advancements, search algorithms can still surface inappropriate or irrelevant content due to factors like model unpredictability, metadata errors, or overlooked design flaws. Such issues can misalign with product goals and user expectations, potentially harming user trust and business outcomes. In this work, we introduce an additional monitoring layer using Large Language Models (LLMs) to enhance content moderation. This additional layer flags content if the user did not intend to search for it. This approach serves as a baseline for product quality assurance, with collected feedback used to refine the initial retrieval mechanisms of the search model, ensuring a safer and more reliable user experience.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。