未能证伪：评估和缓解语言模型中的确认偏见
Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
AI总结：
研究评估了大型语言模型是否表现出确认偏见，并提出干预策略以减少其影响，通过实验发现干预可显著提高规则发现率。
摘要：
确认偏误，即倾向于寻找支持而非挑战自己信念的证据，会阻碍人的推理能力。我们通过适应人类心理学中的规则发现研究来考察大型语言模型（LLMs）是否表现出确认偏误：给定一个三个数字的序列（一个“三元组”），一个代理会进行互动反馈循环，其中它（1）提出一个新的三元组，（2）接收是否满足隐藏规则的反馈，（3）猜测规则。在 eleven 个不同家族和规模的 LLMs 上，我们发现 LLMs 表现出确认偏误，常常提出三元组来确认他们的假设而非尝试证伪。这导致了发现隐藏规则的速度更慢且更不频繁。我们进一步探索了为人类开发的干预策略（例如，鼓励代理考虑反例）。我们发现通过提示 LLMs 以这样的指令进行提示，能够一致地减少 LLMs 的确认偏误，使规则发现率从 42% 提高到 56%。最后，我们通过将干预行为转化为 LLMs 进行消解，展示了在新任务（Blicket 测试）上的良好泛化能力。我们的工作表明，确认偏误是 LLMs 在假设探索中的一个限制，并且可以通过注入为人类设计的干预措施来缓解。
英文摘要：
Confirmation bias, the tendency to seek evidence that supports rather than challenges one's belief, hinders one's reasoning ability. We examine whether large language models (LLMs) exhibit confirmation bias by adapting the rule-discovery study from human psychology: given a sequence of three numbers (a "triple"), an agent engages in an interactive feedback loop where it (1) proposes a new triple, (2) receives feedback on whether it satisfies the hidden rule, and (3) guesses the rule. Across eleven LLMs of multiple families and scales, we find that LLMs exhibit confirmation bias, often proposing triples to confirm their hypothesis rather than trying to falsify it. This leads to a slower and less frequent discovery of the hidden rule. We further explore intervention strategies developed for humans (e.g., encouraging the agent to consider counterexamples). We find that prompting LLMs with such instructions consistently decreases confirmation bias in LLMs, improving rule discovery rates from 42% to 56% on average. Lastly, we mitigate confirmation bias by distilling intervention-induced behavior into LLMs, showing generalization to a new domain (the Blicket test) and beyond rule discovery (mathematical self-correction). Our work shows that confirmation bias is a limitation of LLMs in hypothesis exploration, and that it can be mitigated via injecting interventions designed for humans.
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。
