Large language models (LLMs) have received much attention and shown their
potential in digital health, while their application in mental health is
subject to ongoing debate. This systematic review aims to summarize and
characterize the use of LLMs in mental health by investigating the strengths
and limitations of the latest work in LLMs and discusses the challenges and
opportunities for early screening, digital interventions, and other clinical
applications in mental health. Following PRISMA guidelines, we examined English
articles from PubMed, DBLP Computer Science Bibliography, and IEEE Xplore,
published between 1 January 2017, and 1 September 2023, focusing on mental
health and LLMs. The review analyzed 32 articles, including mental health
analysis using social media datasets (n=13), mental health chatbots (n=10), and
other mental health applications (n=9). Findings reveal LLMs' effectiveness in
mental health issue detection and the enhancement of telepsychological services
through personalised healthcare. Nonetheless, risks like text inconsistencies,
hallucinatory content, and the lack of an ethical framework raise concerns
about their clinical use. Despite these challenges, the advancement of LLMs
underscores their potential as innovative clinical tools, necessitating further
research and development. The review emphasizes that LLMs should complement,
not replace, professional mental health services.

总结和概括了大型语言模型（LLMs）在心理健康领域的应用，包括早期筛查、数字干预和其他临床应用领域的强项、限制、挑战和机遇，并指出了 LLMs 在心理健康问题检测和个性化医疗方面的有效性，同时也提出了关于文本一致性、幻觉内容和缺乏伦理框架的风险以及 LLMs 作为创新临床工具的进一步研究和发展的必要性，强调 LLMs 应该是专业心理健康服务的补充而非替代。

大型语言模型用于心理健康研究的系统综述

Large Language Model for Mental Health: A Systematic Review

Large Language Models (LLM) have shown remarkable language capabilities
fueling attempts to integrate them into applications across a wide range of
domains. An important application area is question answering over private
enterprise documents where the main considerations are data security, which
necessitates applications that can be deployed on-prem, limited computational
resources and the need for a robust application that correctly responds to
queries. Retrieval-Augmented Generation (RAG) has emerged as the most prominent
framework for building LLM-based applications. While building a RAG is
relatively straightforward, making it robust and a reliable application
requires extensive customization and relatively deep knowledge of the
application domain. We share our experiences building and deploying an LLM
application for question answering over private organizational documents. Our
application combines the use of RAG with a finetuned open-source LLM.
Additionally, our system, which we call Tree-RAG (T-RAG), uses a tree structure
to represent entity hierarchies within the organization. This is used to
generate a textual description to augment the context when responding to user
queries pertaining to entities within the organization's hierarchy. Our
evaluations show that this combination performs better than a simple RAG or
finetuning implementation. Finally, we share some lessons learned based on our
experiences building an LLM application for real-world use.

构建一个基于 RAG 的 LLM 应用程序，Tree-RAG 使用树结构表示组织中的实体层级，并生成文字描述以增强响应用户查询的上下文。

T-RAG: LLM 战壕中的教训

T-RAG: Lessons from the LLM Trenches

Hallucinations in large language models (LLMs) are always seen as
limitations. However, could they also be a source of creativity? This survey
explores this possibility, suggesting that hallucinations may contribute to LLM
application by fostering creativity. This survey begins with a review of the
taxonomy of hallucinations and their negative impact on LLM reliability in
critical applications. Then, through historical examples and recent relevant
theories, the survey explores the potential creative benefits of hallucinations
in LLMs. To elucidate the value and evaluation criteria of this connection, we
delve into the definitions and assessment methods of creativity. Following the
framework of divergent and convergent thinking phases, the survey
systematically reviews the literature on transforming and harnessing
hallucinations for creativity in LLMs. Finally, the survey discusses future
research directions, emphasizing the need to further explore and refine the
application of hallucinations in creative processes within LLMs.

大型语言模型（LLM）中的幻觉被视为限制，但是它们是否也可能是创造力的源泉？本研究探讨了这个可能性，认为幻觉可能通过促进创造力来促进 LLM 应用。通过回顾幻觉的分类及其对 LLM 在关键应用中可靠性的负面影响的调查，本研究开始讨论幻觉在 LLM 中的潜在创造性益处，通过历史案例和最新相关理论，深入研究了幻觉在 LLM 中实现创造力的价值和评估标准。根据发散和收敛思维阶段的框架，本研究系统地回顾了利用 LLM 中的幻觉进行创造力转化和利用的文献。最后，本研究讨论了未来的研究方向，强调进一步探索和完善 LLM 中幻觉在创造过程中的应用的必要性。