LLM生成的黑盒解释可能具有对抗性的帮助性
LLM-Generated Black-box Explanations Can Be Adversarially Helpful
AI总结：
本文揭示了LLMs在黑盒解释中存在的“对抗性帮助性”风险，即通过重新表述问题、表达高信心和挑选证据等策略使错误答案看似正确，从而误导人类和LLM评估器，并基于图导航实验指出其误导并非源于复杂逻辑推演。
摘要：
大型语言模型（LLMs）正成为帮助我们解决和理解复杂问题的重要工具，它们充当着数字助手的角色。LLMs能够生成令人信服的解释，即使仅给定这些问题的输入和输出，即采用“黑盒”方法。然而，我们的研究揭示了与这种方法相关的一个隐藏风险，我们称之为*对抗性帮助性*。这种情况发生在LLM的解释使错误答案看起来正确时，可能导致人们信任错误的解决方案。在本文中，我们展示了这个问题不仅影响人类，也影响LLM评估器。深入挖掘后，我们识别并检查了LLMs采用的关键说服策略。我们的发现表明，这些模型采用诸如重新表述问题、表达更高水平的信心以及挑选证据等策略，以可信的方式描绘误导性答案。为了检验LLMs在生成对抗性帮助性解释时是否能够导航复杂结构的知识，我们创建了一个基于图导航的特殊任务。大多数LLMs无法在简单图中找到替代路径，这表明它们的误导性解释并非仅通过使用复杂知识的逻辑推演产生。这些发现揭示了黑盒解释设置的局限性，并使我们能够提供关于LLMs安全使用的建议。
英文摘要：
Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these problems, i.e., in a ``black-box'' approach. However, our research uncovers a hidden risk tied to this approach, which we call *adversarial helpfulness*. This happens when an LLM's explanations make a wrong answer look right, potentially leading people to trust incorrect solutions. In this paper, we show that this issue affects not just humans, but also LLM evaluators. Digging deeper, we identify and examine key persuasive strategies employed by LLMs. Our findings reveal that these models employ strategies such as reframing the questions, expressing an elevated level of confidence, and cherry-picking evidence to paint misleading answers in a credible light. To examine if LLMs are able to navigate complex-structured knowledge when generating adversarially helpful explanations, we create a special task based on navigating through graphs. Most LLMs are not able to find alternative paths along simple graphs, indicating that their misleading explanations aren't produced by only logical deductions using complex knowledge. These findings shed light on the limitations of the black-box explanation setting and allow us to provide advice on the safe usage of LLMs.
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。
