微调数据预处理方式影响 LLM 推荐效果与人口群体敏感性
Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation
想在推荐系统里用 LLM 的朋友看这篇：同一份 MovieLens-1M 数据，光换标题格式 HR@10 就差了近 2 个点，性别平衡还有副作用，细节都在这了。
论文研究了微调数据预处理如何影响基于 LLM 的生成式推荐系统。作者搭建了结合监督微调、catalog 约束解码和 prompt 增强的流水线，在 MovieLens-1M 上测试了三个预处理维度：条目标题表示、人口属性平衡和条目知识增强。使用原始 MovieLens 标题使 HR@10 从 10.67% 提升到 12.47%，Coverage@10 从 41.36% 提升到 47.88%。年龄平衡和知识增强能缩小群体间效用差距，而性别平衡反而降低效用且未改善性别相关指标。
Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation
Large language models (LLMs) have introduced a generative approach to recommendation, producing item lists from textual representations of user histories and item information. However, this generative setting raises challenges concerning output validity, prompt consistency, and sensitivity to demographic descriptors. In this work, we investigate how preprocessing choices in fine-tuning data affect recommendation utility and fairness-related behavior in a generative LLM-based recommender system. We first establish a controlled recommendation pipeline that combines supervised fine-tuning, catalog-constrained decoding, and prompt augmentation. We then study three preprocessing choices: item-title representation, demographic balancing, and auxiliary item-knowledge enrichment. Experiments on MovieLens-1M show that the catalog-constrained pipeline eliminates out-of-catalog items and ensures complete ten-item outputs, while prompt augmentation improves prompt consistency and utility. Original MovieLens titles increase HR@10 from 10.67% to 12.47% and Coverage@10 from 41.36% to 47.88%. Fairness-related effects are attribute-dependent: age balancing and knowledge enrichment reduce selected group-level utility gaps while largely preserving utility, whereas gender balancing reduces utility without improving the evaluated gender-related indicators. Overall, preprocessing choices in fine-tuning data should be evaluated jointly in terms of utility, output behavior, and demographic sensitivity.