Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM's process for solving a task. This level of transparency into LLMs' predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model's prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs--e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always "(A)"--which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods.

翻译：大型语言模型（LLMs）通过生成逐步推理（即思维链推理，CoT）后再输出最终答案，能在许多任务上取得优异表现。人们倾向于将这些CoT解释视为LLM求解任务的内在过程，这种对LLM预测的透明化将带来显著的安全效益。然而我们发现，CoT解释可能系统性地歪曲模型预测的真实原因。实验表明，在模型输入中添加偏置特征（例如通过重新排列少样本提示中的多选题选项使答案始终为"(A)"），会显著影响CoT解释的内容，而模型在解释中却系统性地忽略了这些偏置因素。当我们引导模型偏向错误答案时，模型频繁生成为这些错误答案合理化辩护的CoT解释。在对OpenAI的GPT-3.5和Anthropic的Claude 1.0进行测试时，这种方法导致BIG-Bench Hard基准套件中13个任务的平均准确率下降高达36%。在社会偏见任务中，模型的解释会合理化符合刻板印象的答案，却完全不提及这些社会偏见的影响。我们的研究结果表明，CoT解释可能看似合理实则具有误导性，这将在不保证安全性的前提下增加我们对LLM的信任。要构建更透明、可解释的系统，要么需要有针对性的努力改进CoT的忠实度，要么放弃CoT转而采用其他方法。