用真人对话数据训练大模型，让其性格更真实自然。
BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
- 基于10万条真人对话数据，用微调和偏好优化训练模型。
- 性格测试得分优于提示法，与人类数据相关性更高。
- 高尽责、高宜人性的模型推理能力更强，符合心理学规律。
本文致力于将真实的人类性格特征嵌入大语言模型。以往方法多依赖提示工程描述目标性格行为，存在真实性和有效性不足的问题。为此，我们提出BIG5-CHAT，一个包含10万条对话的大规模数据集，旨在通过真实人类语言表达来刻画性格特征。基于该数据集，我们探索了监督微调和直接偏好优化两种训练方法，使模型更自然地匹配人类性格模式。实验表明，该方法在BFI和IPIP-NEO等性格评估中表现优于提示法，性格相关性更接近真实人类数据。此外，训练出的高尽责性、高宜人性、低外向性、低神经质性的模型在推理任务上表现更优，与心理学研究中关于这些特质影响认知表现的结论一致。据我们所知，这是首个系统性展示通过学习真实人类行为来塑造大模型性格的研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。