使用大语言模型预测中文心理咨询对话中的大五人格特质
Predicting the Big Five Personality Traits in Chinese Counselling Dialogues Using Large Language Models
AI总结：
本研究提出基于角色扮演和问卷提示的创新框架，利用大语言模型直接从中文心理咨询对话中预测大五人格特质，其微调后的Llama3-8B模型在预测效度上显著超越现有大模型。
摘要：
准确评估人格特质对于有效的心理咨询至关重要，然而传统的自陈问卷等方法既耗时又存在偏差。本研究探讨大语言模型（LLMs）能否直接从心理咨询对话中预测大五人格特质，并引入一个创新框架来执行该任务。我们的框架应用角色扮演和基于问卷的提示来对LLMs进行心理咨询会话的条件约束，模拟来访者对大五量表（Big Five Inventory）的回答。我们在853次真实心理咨询会话上评估了该框架，发现LLM预测的与实际的大五人格特质之间存在显著相关性，证明了框架的有效性。此外，消融研究突出了角色扮演模拟和通过问卷简化任务在提升预测准确性方面的重要性。同时，我们微调的Llama3-8B模型利用带监督微调的直接偏好优化，实现了130.95%的提升，在人格预测效度上超越了最先进的Qwen1.5-110B 36.94%。总之，LLMs能够基于心理咨询对话预测人格。我们的代码和模型已在https://github.com/kuri-leo/BigFive-LLM-Predictor公开发布，为计算心理测量学的未来研究提供了宝贵工具。
英文摘要：
Accurate assessment of personality traits is crucial for effective psycho-counseling, yet traditional methods like self-report questionnaires are time-consuming and biased. This study exams whether Large Language Models (LLMs) can predict the Big Five personality traits directly from counseling dialogues and introduces an innovative framework to perform the task. Our framework applies role-play and questionnaire-based prompting to condition LLMs on counseling sessions, simulating client responses to the Big Five Inventory. We evaluated our framework on 853 real-world counseling sessions, finding a significant correlation between LLM-predicted and actual Big Five traits, proving the validity of framework. Moreover, ablation studies highlight the importance of role-play simulations and task simplification via questionnaires in enhancing prediction accuracy. Meanwhile, our fine-tuned Llama3-8B model, utilizing Direct Preference Optimization with Supervised Fine-Tuning, achieves a 130.95\% improvement, surpassing the state-of-the-art Qwen1.5-110B by 36.94\% in personality prediction validity. In conclusion, LLMs can predict personality based on counseling dialogues. Our code and model are publicly available at \url{https://github.com/kuri-leo/BigFive-LLM-Predictor}, providing a valuable tool for future research in computational psychometrics.
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。
