用LLM预测成人依恋关系:聊天式探索
Chatting Up Attachment: Using LLMs to Predict Adult Bonds
AI总结:
本文利用GPT-4和Claude 3 Opus生成模拟成人依恋访谈的合成数据,训练模型预测依恋风格,证明仅用合成数据可达到与人类数据相当的性能,并通过引入未标注人类数据和标准化实现表示对齐与预测提升。
摘要:
在医疗领域获取数据具有挑战性,这使得人工智能技术在该领域的应用进展缓慢且风险较高。我们评估是否能够利用大型语言模型(LLMs)生成的合成数据来克服这一障碍。具体而言,我们使用GPT-4和Claude 3 Opus创建智能体,模拟具有不同个人背景、童年记忆和依恋风格的成年人。这些智能体参与模拟的成人依恋访谈(AAI),我们利用它们的回答来训练模型,以预测其潜在的依恋风格。我们使用来自9名接受相同访谈协议的人类受试者的转录数据集对模型进行评估,该数据集由心理健康专业人员进行分析和标注。我们的研究结果表明,仅使用合成数据训练的模型,其性能与使用人类数据训练的模型相当。此外,虽然来自合成答案的原始嵌入与来自真实人类回答的原始嵌入占据不同的空间,但引入未标注的人类数据并进行简单的标准化处理,可以使这些表示更加对齐。这一调整得到了定性分析的支持,并体现在标准化嵌入的预测准确性提升上。
英文摘要:
Obtaining data in the medical field is challenging, making the adoption of AI technology within the space slow and high-risk. We evaluate whether we can overcome this obstacle with synthetic data generated by large language models (LLMs). In particular, we use GPT-4 and Claude 3 Opus to create agents that simulate adults with varying profiles, childhood memories, and attachment styles. These agents participate in simulated Adult Attachment Interviews (AAI), and we use their responses to train models for predicting their underlying attachment styles. We evaluate our models using a transcript dataset from 9 humans who underwent the same interview protocol, analyzed and labeled by mental health professionals. Our findings indicate that training the models using only synthetic data achieves performance comparable to training the models on human data. Additionally, while the raw embeddings from synthetic answers occupy a distinct space compared to those from real human responses, the introduction of unlabeled human data and a simple standardization allows for a closer alignment of these representations. This adjustment is supported by qualitative analyses and is reflected in the enhanced predictive accuracy of the standardized embeddings.
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。