发现大模型有确认偏见，用人类干预方法可有效改善其推理能力。
Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
- 通过模仿人类试错实验，测试模型是否只找支持假设的证据。
- 未经干预时模型规则发现率仅42%，经提示后提升至56%。
- 将人类干预策略注入模型，可推广到新任务，适合改进AI推理设计。
确认偏见指倾向于寻找支持已有信念而非挑战它的证据，这会削弱推理能力。我们借鉴人类心理学中的规则发现实验，考察大语言模型（LLMs）是否存在确认偏见：给定一个三元组序列，模型在交互反馈中提出新三元组，接收是否符合隐藏规则的反馈，并猜测规则。在11个不同家族与规模的LLM上，我们发现模型普遍表现出确认偏见，倾向于提出支持假设的三元组，而非尝试证伪，导致规则发现更慢且更少。我们进一步测试了为人类设计的干预策略（如鼓励考虑反例），发现用此类指令提示模型能持续降低其确认偏见，平均将规则发现率从42%提升至56%。最后，我们通过知识蒸馏将干预行为融入模型，在新任务——Blicket测试中展现出良好泛化能力。研究显示，确认偏见是大模型在假设探索中的局限，但可通过注入人类干预策略加以缓解。
原文摘要 · Abstract (English)
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 slower and less frequent discovery of the hidden rule. We further explore intervention strategies (e.g., encouraging the agent to consider counter examples) developed for humans. We find prompting LLMs with such instruction 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 promising generalization to a new task, the Blicket test. 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。