多模态旅游推荐系统中的数据质量问题研究
Data Quality Challenges in Multimodal Tourism Recommender Systems
做推荐系统的可以看看，论文用 Yelp 和 Instagram 的真实数据盘点了假评论、LLM 幻觉、模态矛盾这些坑，还给了质量感知融合这类改法。现在大家都在往多模态堆数据，这篇正好提醒先检查数据质量。
一篇新论文聚焦旅游推荐场景，检视了来自 Yelp 和 Instagram 的真实数据集在多模态推荐中遇到的质量问题。作者归纳出四类典型缺陷：虚假评论带来的噪声、LLM 生成内容中的幻觉、不同模态之间的信息矛盾，以及人口统计层面的偏差。
论文指出，尽管推荐系统越来越多地引入文本、图像等多模态数据来提升性能，底层多模态数据质量却长期被忽视。为此作者提出三条改进方向：引入质量感知的融合机制、采用结构化且可控的 LLM 内容生成来减少幻觉输出、按用户群体差异化建模以增强系统鲁棒性。
对开发者而言，这篇论文的价值在于提供了基于真实平台数据的失效案例分析，适合正在构建多模态推荐或 RAG 类系统的团队对照排查自己的数据管线。
Data Quality Challenges in Multimodal Tourism Recommender Systems
Modern recommender systems increasingly consider diverse data modalities to enhance model performance. However, the quality of the underlying multimodal data (e.g. data from social media platforms) has received limited attention so far. Focusing on tourism recommendation, we examine real-world challenges encountered when using datasets from Yelp and Instagram. Issues include noise from fake reviews, hallucinated content from LLMs, modality contradictions, and demographic bias. We outline future directions such as quality-aware fusion, structured and controlled LLM-based content generation to reduce hallucinations, and user group differentiation to improve the robustness and reliability of multimodal recommendation systems.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include 推荐系统, 多模态, LLM幻觉, 数据质量.
Source attribution: curated from arXiv cs.LG (@Zehui Wang, Wolfram Höpken, Dietmar Jannach).
