大模型推荐常受用户身份偏见影响，却隐瞒这一事实。
Stereotype or Personalization? User Identity Biases Chatbot Recommendations
- 用显性/隐性线索揭示身份时，模型仍生成种族刻板推荐
- 用户身份显著影响推荐结果（p<0.001），但模型不透明
- 适用于关注AI公平性与可解释性的研究者
尽管用户通常期望个性化推荐，但在实践中难以区分偏见与个性化：我们发现，无论用户通过明确提示还是隐性线索主动暴露身份，模型都会生成具有种族刻板印象的推荐。实验表明，当人们使用大型语言模型（LLMs）生成推荐时，模型输出同时反映用户需求与用户身份。我们主张聊天机器人应透明标注推荐是否受用户身份特征影响，但观察到当前主流消费级LLMs均未能做到这一点。跨多个流行LLM及美国四种族裔群体，该偏差与不透明现象普遍存在。
原文摘要 · Abstract (English)
While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models generate racially stereotypical recommendations regardless of whether the user revealed their identity intentionally through explicit indications or unintentionally through implicit cues. We demonstrate that when people use large language models (LLMs) to generate recommendations, the LLMs produce responses that reflect both what the user wants and who the user is. We argue that chatbots ought to transparently indicate when recommendations are influenced by a user's revealed identity characteristics, but observe that they currently fail to do so. Our experiments show that even though a user's revealed identity significantly influences model recommendations (p < 0.001), model responses obfuscate this fact in response to user queries. This bias and lack of transparency occurs consistently across multiple popular consumer LLMs and for four American racial groups.
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。