A cognitive layer architecture to support large-language model performance in psychotherapy interactions.

Large language models (LLMs) could hold promise for this domain but their effectiveness in patient-facing interactions remains largely unproven.

大型语言模型（LLMs）可能对此领域抱有希望，但其在面向患者交互中的有效性仍然在很大程度上未经证实。

Here we introduce a cognitive layer architecture that enhances general-purpose LLMs with specialized clinical psychotherapeutic reasoning capabilities.

在此，我们介绍了一种认知层架构，该架构增强了通用大型语言模型（LLMs）的特定临床心理治疗推理能力。

In a randomized, double-blindevaluation, 227 human participants generated naturalistic mental well-being session transcripts by interacting with different therapy agents.

在一项随机、双盲评估中，227名人类参与者通过与不同的治疗代理互动，生成了自然化的心理健康会话记录。

A consortium of 22 expert clinicians assessed these transcripts, finding that LLMs augmented with this architecture consistently outperformed both standalone state-of-the-art LLMs and human clinicians across key clinical competencies required for delivering high-quality cognitive-behavioral therapy.

一个由22位专家临床医生组成的联盟评估了这些记录，发现采用这种架构增强的大型语言模型（LLMs）在交付高质量认知行为疗法所需的关键临床能力方面，始终优于最先进的独立大型语言模型和人类临床医生。

We validated these results in an analysis of 19,674 transcripts from a large-scale, real-world deployment where an LLM embedded within this cognitive layer architecture was used as part of healthcare delivery to support 8,920 users seeking mental well-being assistance.

我们在一项分析中验证了这些结果，该分析涉及19,674份记录，来自大规模、现实世界中的部署，其中嵌入了这种认知层架构的大型语言模型（LLM）被用作医疗交付的一部分，以支持8,920名寻求心理健康帮助的用户。

Increased cognitive layer activation was associated with greater symptom improvement and a higher likelihood of long-term clinical recovery (~10 weeks).

认知层活动的增加与症状改善程度更大以及长期临床恢复（约10周）的可能性更高有关。

Our findings demonstrate that a cognitive layer architecture can enable LLMs to deliver high-quality cognitive-behavioral therapy interactions, with continued research warranted into mechanisms and clinical efficacy of AI-assisted therapeutics.

我们的发现表明，认知层架构可以使大型语言模型（LLMs）提供高质量的认知行为疗法互动，对于人工智能辅助治疗的机制和临床疗效的持续研究是必要的。