通过提示提升大型语言模型的心智理论性能
Boosting Theory-of-Mind Performance in Large Language Models via Prompting
AI总结：
本文评估GPT-4与GPT-3.5变体的心智理论任务表现，发现上下文思维链提示可显著提升RLHF训练模型的准确率，GPT-4甚至达到100%。
摘要：
2023年，大型语言模型（LLM）在许多任务上表现出色，但它们在复杂推理方面仍面临挑战。心智理论（ToM）任务要求理解智能体的信念、目标和心理状态，对于涉及人类的常识推理至关重要，因此提升LLM在该领域的性能十分关键。本研究衡量了GPT-4以及三种GPT-3.5变体（Davinci-2、Davinci-3、GPT-3.5-Turbo）的ToM性能，并考察了上下文学习在提升其ToM理解方面的有效性。我们评估了包含两次示例思维链推理和逐步思考指令的提示。结果发现，采用基于人类反馈的强化学习（RLHF）训练的LLM（除Davinci-2之外的所有模型）通过上下文学习提高了ToM准确率。GPT-4在零样本设置下表现最佳，ToM准确率接近80%，但仍低于测试集上87%的人类准确率。然而，当提供用于上下文学习的提示时，所有经RLHF训练的LLM的ToM准确率均超过80%，其中GPT-4达到100%。这些结果表明，适当的提示能够增强LLM的ToM推理，并凸显了LLM认知能力依赖于上下文的性质。
英文摘要：
Large language models (LLMs) excel in many tasks in 2023, but they still face challenges in complex reasoning. Theory-of-mind (ToM) tasks, which require understanding agents' beliefs, goals, and mental states, are essential for common-sense reasoning involving humans, making it crucial to enhance LLM performance in this area. This study measures the ToM performance of GPT-4 and three GPT-3.5 variants (Davinci-2, Davinci-3, GPT-3.5-Turbo), and investigates the effectiveness of in-context learning in improving their ToM comprehension. We evaluated prompts featuring two-shot chain of thought reasoning and step-by-step thinking instructions. We found that LLMs trained with Reinforcement Learning from Human Feedback (RLHF) (all models excluding Davinci-2) improved their ToM accuracy via in-context learning. GPT-4 performed best in zero-shot settings, reaching nearly 80% ToM accuracy, but still fell short of the 87% human accuracy on the test set. However, when supplied with prompts for in-context learning, all RLHF-trained LLMs exceeded 80% ToM accuracy, with GPT-4 reaching 100%. These results demonstrate that appropriate prompting enhances LLM ToM reasoning, and they underscore the context-dependent nature of LLM cognitive capacities.
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。
