在大型語言模型中釋放認知協同作用：透過多位角色自我協作的任務解決代理程序

Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

July 11, 2023

作者: Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji

cs.AI

摘要

人類智慧蓬勃發展在認知協同的概念上，其中不同認知過程之間的合作和信息整合產生比單獨認知過程更優越的結果。儘管大型語言模型（LLMs）已經展示出作為通用任務解決代理的有希望的表現，但它們仍然在需要密集領域知識和複雜推理的任務上遇到困難。在這項工作中，我們提出了獨奏表現提示（SPP），通過與多個人格進行多輪自我協同合作，將單個LLM轉化為認知協同者。認知協同者指的是一個智能代理，與多個思維合作，結合他們各自的優勢和知識，以增強解決問題和複雜任務中的整體表現。通過根據任務輸入動態識別和模擬不同的人格，SPP發揮了LLMs中認知協同的潛力。我們發現，在LLMs中分配多個細粒度的人格比使用單個或固定數量的人格能更好地引發解決問題的能力。我們在三個具有挑戰性的任務上評估了SPP：知識創意寫作、代號合作和邏輯網格拼圖，包括知識密集型和推理密集型。與先前的作品（如Chain-of-Thought）不同，它僅增強LLMs中的推理能力，SPP有效地引發了內部知識獲取能力，減少了幻覺並保持了強大的推理能力。代碼、數據和提示可在以下鏈接找到：https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git。

English

Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among different cognitive processes yield superior outcomes compared to individual cognitive processes in isolation. Although Large Language Models (LLMs) have demonstrated promising performance as general task-solving agents, they still struggle with tasks that require intensive domain knowledge and complex reasoning. 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 refers to an intelligent agent that collaborates with multiple minds, combining their individual strengths and knowledge, to enhance problem-solving and overall performance in complex tasks. By dynamically identifying and simulating different personas based on task inputs, SPP unleashes the potential of cognitive synergy in LLMs. We have discovered that assigning multiple, fine-grained personas in LLMs elicits better 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, SPP effectively elicits internal knowledge acquisition abilities, reduces hallucination, and maintains strong reasoning capabilities. Code, data, and prompts can be found at: https://github.com/MikeWangWZHL/Solo-Performance-Prompting.git.