用大模型帮用户过滤令人不适的推荐，让推荐更贴心。
Filtering Discomforting Recommendations with Large Language Models
- 用大模型对话构建可编辑的用户偏好档案，识别不适内容
- 3.8B开源模型在离线任务中达到商用顶级水平
- 适合关注推荐系统伦理与用户体验的研究者
个性化算法可能无意中向用户推送令人不适的推荐，引发负面后果。由于不适感具有主观性且算法为黑箱，有效识别和过滤此类内容颇具挑战。为此，我们首先开展前期研究，了解用户对不适推荐过滤的行为与期望。随后设计基于大语言模型（LLM）的工具 DiscomfortFilter，通过对话帮助用户构建可编辑的偏好档案，以表达过滤需求，从而隐藏档案中的不适偏好。基于修改后的档案，DiscomfortFilter以即插即用方式实现不适推荐过滤，兼具灵活性与透明性。该偏好档案提升了大模型推理能力，简化了用户对齐过程，使一个3.8B的开源模型在离线代理任务中媲美顶尖商业模型。为期一周的24人用户研究表明，DiscomfortFilter有效提升过滤效果，同时揭示其对平台推荐结果的潜在影响。最后，我们讨论持续挑战、研究意义、利益相关方影响及未来方向。
原文摘要 · Abstract (English)
Personalized algorithms can inadvertently expose users to discomforting recommendations, potentially triggering negative consequences. The subjectivity of discomfort and the black-box nature of these algorithms make it challenging to effectively identify and filter such content. To address this, we first conducted a formative study to understand users' practices and expectations regarding discomforting recommendation filtering. Then, we designed a Large Language Model (LLM)-based tool named DiscomfortFilter, which constructs an editable preference profile for a user and helps the user express filtering needs through conversation to mask discomforting preferences within the profile. Based on the edited profile, DiscomfortFilter facilitates the discomforting recommendations filtering in a plug-and-play manner, maintaining flexibility and transparency. The constructed preference profile improves LLM reasoning and simplifies user alignment, enabling a 3.8B open-source LLM to rival top commercial models in an offline proxy task. A one-week user study with 24 participants demonstrated the effectiveness of DiscomfortFilter, while also highlighting its potential impact on platform recommendation outcomes. We conclude by discussing the ongoing challenges, highlighting its relevance to broader research, assessing stakeholder impact, and outlining future research directions.
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。