BIG5-CHAT：通过基于人类数据的训练塑造大语言模型（LLM）人格
BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
AI总结：
本研究针对基于提示词的LLM人格塑造方法真实性不足的问题，推出含10万条对话的BIG5-CHAT数据集，采用有监督微调和直接偏好优化训练，提升人格匹配度并验证部分人格特质与推理能力的关联。
摘要：
在本研究中，我们应对将真实人类人格特质嵌入大语言模型（LLM）的挑战。此前的方法主要聚焦于基于提示词的方法，这类方法描述与目标人格特质相关的行为，存在真实性和有效性问题。为解决这些局限，我们推出BIG5-CHAT，这是一个包含10万条对话的大规模数据集，旨在让模型掌握人类如何通过语言表达人格。借助该数据集，我们探索了有监督微调（Supervised Fine-Tuning）和直接偏好优化（Direct Preference Optimization）这两种基于训练的方法，以使LLM更自然地契合人类人格模式。我们的方法在BFI、IPIP-NEO等人格测评中的表现优于提示词方法，特质相关性与人类数据更为匹配。此外，我们的实验显示，经过训练表现出更高尽责性、更高宜人性、更低外向性和更低神经质的模型在推理任务上表现更佳，这与关于这些特质如何影响人类认知表现的心理学研究结果一致。据我们所知，本研究是首个全面证明基于训练的方法可通过学习真实人类行为来塑造LLM人格的研究。
英文摘要：
In this work, we tackle the challenge of embedding realistic human personality traits into LLMs. Previous approaches have primarily focused on prompt-based methods that describe the behavior associated with the desired personality traits, suffering from realism and validity issues. To address these limitations, we introduce BIG5-CHAT, a large-scale dataset containing 100,000 dialogues designed to ground models in how humans express their personality in language. Leveraging this dataset, we explore Supervised Fine-Tuning and Direct Preference Optimization as training-based methods to align LLMs more naturally with human personality patterns. Our methods outperform prompting on personality assessments such as BFI and IPIP-NEO, with trait correlations more closely matching human data. Furthermore, our experiments reveal that models trained to exhibit higher conscientiousness, higher agreeableness, lower extraversion, and lower neuroticism display better performance on reasoning tasks, aligning with psychological findings on how these traits impact human cognitive performance. To our knowledge, this work is the first comprehensive study to demonstrate how training-based methods can shape LLM personalities through learning from real human behaviors.
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。
