用心理偏见操控大模型推荐，让商品更易被推荐
Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations
- 利用社会认同等心理偏见改写商品描述，隐蔽诱导推荐
- 社会认同显著提升商品推荐率与排名，稀缺性反而降低可见度
- 揭示大模型推荐的不可预测性，适合关注安全与商业应用者
大型语言模型（LLMs）革新了产品推荐系统，但其易受对抗性操纵的特性在真实商业场景中带来严峻挑战。本文首次引入人类心理机制，通过无缝修改商品描述实现隐蔽操纵。我们研究认知偏见作为黑箱对抗策略，发现社会认同等偏见能持续提升商品推荐率与排名，而稀缺性与排他性偏见反而降低商品可见度。在多种规模模型上的评估表明，认知偏见深度嵌入当前主流大模型中，导致推荐行为高度不可预测，对有效缓解策略构成重大挑战。
原文摘要 · Abstract (English)
The advent of Large Language Models (LLMs) has revolutionized product recommenders, yet their susceptibility to adversarial manipulation poses critical challenges, particularly in real-world commercial applications. Our approach is the first one to tap into human psychological principles, seamlessly modifying product descriptions, making such manipulations hard to detect. In this work, we investigate cognitive biases as black-box adversarial strategies, drawing parallels between their effects on LLMs and human purchasing behavior. Through extensive evaluation across models of varying scale, we find that certain biases, such as social proof, consistently boost product recommendation rate and ranking, while others, like scarcity and exclusivity, surprisingly reduce visibility. Our results demonstrate that cognitive biases are deeply embedded in state-of-the-art LLMs, leading to highly unpredictable behavior in product recommendations and posing significant challenges for effective mitigation.
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。