PersLLM：一种面向大语言模型的人格化训练方法
PersLLM: A Personified Training Approach for Large Language Models
AI总结：
本文提出 PersLLM 框架，通过思维链与反归纳数据构建及自动化 DPO 调优，增强大语言模型人格的真实性、持续性与动态表达能力。
摘要：
大语言模型（LLM）展现出类人智能，使其能够模拟人类行为，并支持各类同时需要人性化交流和丰富知识储备的应用。已有研究尝试通过特殊训练数据或手工编写的提示词使 LLM 人格化，但相应面临数据利用不足或行为模式僵化等挑战。因此，人格化 LLM 无法掌握人格化知识，也无法表达持续一致的观点。为充分释放 LLM 人格化的潜力，我们提出 PersLLM，这是一个用于改进数据构建和模型调优的框架。针对数据利用不足，我们引入 Chain-of-Thought prompting（思维链提示）和反归纳等策略，提高数据构建质量，并更全面地捕捉人格经验、知识和思想。针对行为模式僵化，我们设计了调优流程，并引入自动化 DPO，以增强模型人格的特异性和动态性，从而实现更自然的观点交流。自动化指标和专家人工评估均证明了本方法的有效性。人机交互和多智能体系统中的案例研究进一步展示了 LLM 人格化的潜在应用场景和未来方向。
英文摘要：
Large language models (LLMs) exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. Efforts are made to personify LLMs with special training data or hand-crafted prompts, while correspondingly faced with challenges such as insufficient data usage or rigid behavior patterns. Consequently, personified LLMs fail to capture personified knowledge or express persistent opinion. To fully unlock the potential of LLM personification, we propose PersLLM, a framework for better data construction and model tuning. For insufficient data usage, we incorporate strategies such as Chain-of-Thought prompting and anti-induction, improving the quality of data construction and capturing the personality experiences, knowledge, and thoughts more comprehensively. For rigid behavior patterns, we design the tuning process and introduce automated DPO to enhance the specificity and dynamism of the models' personalities, which leads to a more natural opinion communication. Both automated metrics and expert human evaluations demonstrate the effectiveness of our approach. Case studies in human-machine interactions and multi-agent systems further suggest potential application scenarios and future directions for LLM personification.
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。
