释放大型语言模型中涌现的认知协同：通过多角色自协作实现的任务解决智能体
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
AI总结：
本文提出Solo Performance Prompting (SPP)，通过多角色自协作将单个LLM转化为认知协同者，在知识密集与推理密集任务中减少事实幻觉并保持强推理能力，且发现认知协同仅在GPT-4中涌现。
摘要：
人类智能的繁荣依赖于认知协同，即不同思维之间的协作能产生优于孤立个体的结果。在本研究中，我们提出了Solo Performance Prompting (SPP)，通过参与多角色多轮自协作，将单个LLM转化为认知协同者。认知协同者是一种智能体，它协同结合多种思维的优势和知识，以增强复杂任务中的问题解决能力。通过根据任务输入动态识别和模拟不同角色，SPP释放了LLM中认知协同的潜力。我们的深入分析表明，在LLM中分配多个细粒度角色，与使用单一或固定数量角色相比，能提升问题解决能力。我们在三个具有挑战性的任务上评估了SPP：Trivia Creative Writing、Codenames Collaborative和Logic Grid Puzzle，涵盖了知识密集型和推理密集型类型。与Chain-of-Thought等仅增强LLM推理能力的先前工作不同，实验结果表明，SPP有效减少了事实幻觉，并保持了强大的推理能力。此外，对比实验显示，认知协同仅在GPT-4中涌现，而未出现在GPT-3.5-turbo和Llama2-13b-chat等能力较弱的模型中，这为人类发展提供了有趣的类比。代码、数据和提示可在：https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git 找到。
英文摘要：
Human intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. A cognitive synergist is an intelligent agent that collaboratively combines multiple minds' strengths and knowledge to enhance problem-solving in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. Our in-depth analysis shows that assigning multiple fine-grained personas in LLMs improves problem-solving abilities compared to using a single or fixed number of personas. We evaluate SPP on three challenging tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle, encompassing both knowledge-intensive and reasoning-intensive types. Unlike previous works, such as Chain-of-Thought, that solely enhance the reasoning abilities in LLMs, experimental results demonstrate that SPP effectively reduces factual hallucination, and maintains strong reasoning capabilities. Additionally, comparative experiments show that cognitive synergy only emerges in GPT-4 and does not appear in less capable models, such as GPT-3.5-turbo and Llama2-13b-chat, which draws an interesting analogy to human development. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.
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。
