arXiv：cs.CL· Gunhee Cho, Yun-Gyung Cheong·· 6 小时前
Big5-Scaler：用大五人格提示词实现 LLM 可控人格
Scaling Personality Control in LLMs with Big Five Scaler Prompts
AI 导读
研究者提出 Big5-Scaler，一个基于提示词的框架，通过将大五人格的数值特征嵌入自然语言提示词，无需额外训练即可对 LLM 实现细粒度人格控制。该框架在特质表达、对话生成和人类特质模仿任务上进行了评估，结果显示其能在不同模型间稳定诱导出可区分的人格特质，且表现随提示词类型和规模而变化。分析表明简洁提示词和较低特质强度更有效，为构建人格感知对话智能体提供了高效方案。
正文
Abstract:We present Big5-Scaler, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits. By embedding numeric trait values into natural language prompts, our method enables fine-grained personality control without additional training. We evaluate Big5-Scaler across trait expression, dialogue generation, and human trait imitation tasks. Results show that it induces consistent and distinguishable personality traits across models, with performance varying by prompt type and scale. Our analysis highlights the effectiveness of concise prompts and lower trait intensities, providing a efficient approach for building personality-aware dialogue agents.
| Subjects: | Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2508.06149 [cs.CL] |
| (or arXiv:2508.06149v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2508.06149 arXiv-issued DOI via DataCite |
Submission history
From: Gunhee Cho [view email]
[v1]
Fri, 8 Aug 2025 09:11:05 UTC (3,855 KB)
[v2]
Wed, 14 Oct 2026 06:13:56 UTC (1,104 KB)
来源：arXiv：cs.CL · arxiv.org