排名盲点：基于大语言模型的文本排序中的决策劫持
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
AI总结：
本文揭示了LLM文本排序中的“排名盲点”，提出决策目标劫持和决策标准劫持两种攻击方法，实证表明其可迫使排序器偏好特定段落，且更强的LLM更易受攻击。
摘要：
大语言模型（LLMs）在诸如段落排序等信息检索任务中已展现出强大的性能。我们的研究考察了LLMs的指令遵循能力如何与多文档比较任务相互作用，识别出我们称之为“排名盲点”（Ranking Blind Spot）的现象，这是LLM在比较评估过程中决策过程的一个特征。我们通过两种方法分析这一排名盲点如何影响LLM评估系统：决策目标劫持（Decision Objective Hijacking），它改变成对排序系统中的评估目标；以及决策标准劫持（Decision Criteria Hijacking），它修改跨排序方案的相关性标准。这些方法展示了内容提供者如何可能影响基于LLM的排序系统，从而影响文档定位。这些攻击旨在迫使LLM排序器偏好特定段落并将其排在顶部。恶意内容提供者可以利用这一弱点，通过攻击排序器来获得额外曝光。在我们的实验中，我们实证表明所提出的攻击在各种LLMs中均有效，并且可以推广到多种排序方案。我们将这些攻击应用于现实示例以展示其有效性。我们还发现更强的LLMs对这些攻击更为脆弱。我们的代码可在以下地址获取：https://github.com/blindspotorg/RankingBlindSpot
英文摘要：
Large Language Models (LLMs) have demonstrated strong performance in information retrieval tasks like passage ranking. Our research examines how instruction-following capabilities in LLMs interact with multi-document comparison tasks, identifying what we term the "Ranking Blind Spot", a characteristic of LLM decision processes during comparative evaluation. We analyze how this ranking blind spot affects LLM evaluation systems through two approaches: Decision Objective Hijacking, which alters the evaluation goal in pairwise ranking systems, and Decision Criteria Hijacking, which modifies relevance standards across ranking schemes. These approaches demonstrate how content providers could potentially influence LLM-based ranking systems to affect document positioning. These attacks aim to force the LLM ranker to prefer a specific passage and rank it at the top. Malicious content providers can exploit this weakness, which helps them gain additional exposure by attacking the ranker. In our experiment, We empirically show that the proposed attacks are effective in various LLMs and can be generalized to multiple ranking schemes. We apply these attack to realistic examples to show their effectiveness. We also found stronger LLMs are more vulnerable to these attacks. Our code is available at: https://github.com/blindspotorg/RankingBlindSpot
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
