LLMs show bias toward sponsored products, but simple prompts can fix it

A new paper reveals that many large language models, including OpenAI's GPT-3.5 Turbo and GPT-4o, exhibit a bias towards recommending sponsored products. Researchers found that these models often suggest more expensive, sponsored options when presented with subtle sponsorship cues in their system prompts. However, a simple thirty-token user prompt requesting a neutral comparison table significantly reduced this bias, cutting sponsored recommendations from nearly 50% to as low as 0% across tested models. AI

影响 Reveals a bias in LLMs towards sponsored products, highlighting the need for user awareness and prompt engineering to ensure neutral recommendations.

排序理由 The cluster contains an academic paper detailing research findings on LLM behavior. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• GPT-3.5 Turbo
• GPT-4o
• GPT-4o-mini
• GPT-oss-120b
• Large language models
• OpenAI
• Wu et al. (2026)

• 论文
• 安全

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →