这篇论文揭示了 LLM 推荐中的赞助偏见，并提供了一个极简的对抗方法——用 30 token 提示词就能大幅降低推荐偏差。做 AI 安全、推荐系统或 LLM 应用的开发者值得一看，可以直接复现实验。
一项研究复现了 Wu 等人（2026）的发现：多数前沿大语言模型在系统提示中包含软赞助线索时，会推荐价格约两倍的赞助航班。研究者对 10 个开源聊天模型和 2 个 OpenAI 模型（gpt-3.5-turbo、gpt-4o）进行了评估，发现原文的结论具有普遍性——例如 gpt-3.5-turbo 的赞助推荐率与原报告接近。关键发现是：一个仅 30 个 token 的用户提示（要求模型先提供中立对比表格）可将开源模型的赞助推荐率从 46.9% 降至 1.0%，OpenAI 模型从 53.0% 降至 0%。研究还揭示了复现过程中的三个隐性实现错误，表明仅靠文字描述不足以准确复现。
Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs
Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorship cue. We reproduce their evaluation on ten open-weight chat models plus the two of their twenty-three models that are still reachable today (gpt-3.5-turbo, gpt-4o). All reported rates in this paper are produced under the same judge the original paper used (gpt-4o); we additionally store every label under an open-weight (gpt-oss-120b) and a smaller proprietary (gpt-4o-mini) judge for an ablation. Three findings emerge. First, a prose description of an LLM evaluation pipeline is not, on its own, sufficient for accurate reproduction: we surfaced three silent implementation failures that each shifted a reported rate by tens of percentage points. Second, the central claims do generalise - the gpt-3.5-turbo logistic-regression intercept of alpha = 0.81 is within four points of the original alpha = 0.86, and 200 of 200 trials on gpt-3.5-turbo and gpt-4o promote a payday lender to a financially distressed user. Third, a thirty-token user prompt that asks the assistant for a neutral comparison table first cuts sponsored recommendation from 46.9% to 1.0% averaged across our ten open-source models, and from 53.0% to 0% averaged across the two OpenAI models. AI literacy and price-comparison portals are likely market-level mitigations; the harmful-product cell is bounded by neither. Raw data, labels and analysis scripts are at https://github.com/akmaier/Paper-LLM-Ads .