你会错吗：使用元认知提示去偏LLM以改善人类决策
Could you be wrong: Debiasing LLMs using a metacognitive prompt for improving human decision making
AI总结：
本文提出利用源自人类决策研究的元认知提示“你会错吗”来对LLM进行去偏，促使模型反思自身偏差并生成矛盾证据与替代方案，为提示工程提供了新途径。
摘要：
识别LLM中的偏差是一个持续进行的过程。由于它们仍在开发中，今天为真的事物明天可能为假。因此，我们需要能够超越当前模型的通用去偏策略。为人类决策去偏而开发的策略提供了一种有前景的方法，因为它们结合了LLM风格的提示干预，旨在决策过程中将潜在知识带入意识。在海量信息上训练的LLM包含关于潜在偏差、反驳论点和矛盾证据的信息，但这些信息只有在被提示时才会被调用。人类决策文献中开发的元认知提示旨在实现这一目标，正如我在此展示的，它们在LLM上显示出前景。我在此关注的提示是“你会错吗？”。在LLM回复之后，该提示引导LLM产生额外信息，包括它们为何如此回答、错误、偏差、矛盾证据和替代方案，这些在它们最初的回复中都不明显。事实上，这种元知识经常揭示LLM和用户如何解释提示并不一致。在此，我使用一组取自近期关于LLM偏差文章的问题来演示该提示，包括隐性歧视性偏差和元认知失败。“你会错吗”提示LLM识别其自身偏差并产生有说服力的元认知反思。我还展示了另一个涉及令人信服但不完整信息的例子，该信息很容易被元认知提示纠正。总之，这项工作论证了人类心理学为提示工程提供了一条新途径，利用了基于提示改善人类决策的悠久历史。
英文摘要：
Identifying bias in LLMs is ongoing. Because they are still in development, what is true today may be false tomorrow. We therefore need general strategies for debiasing that will outlive current models. Strategies developed for debiasing human decision making offer one promising approach as they incorporate an LLM-style prompt intervention designed to bring latent knowledge into awareness during decision making. LLMs trained on vast amounts of information contain information about potential biases, counter-arguments, and contradictory evidence, but that information may only be brought to bear if prompted. Metacognitive prompts developed in the human decision making literature are designed to achieve this, and as I demonstrate here, they show promise with LLMs. The prompt I focus on here is "could you be wrong?" Following an LLM response, this prompt leads LLMs to produce additional information, including why they answered as they did, errors, biases, contradictory evidence, and alternatives, none of which were apparent in their initial response. Indeed, this metaknowledge often reveals that how LLMs and users interpret prompts are not aligned. Here I demonstrate this prompt using a set of questions taken from recent articles about LLM biases, including implicit discriminatory biases and failures of metacognition. "Could you be wrong" prompts the LLM to identify its own biases and produce cogent metacognitive reflection. I also present another example involving convincing but incomplete information, which is readily corrected by the metacognitive prompt. In sum, this work argues that human psychology offers a new avenue for prompt engineering, leveraging a long history of effective prompt-based improvements to human decision making.
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。
