Using large language models in psychology

D Demszky, D Yang, DS Yeager, CJ Bryan… - Nature Reviews …, 2023 - nature.com
Large language models (LLMs), such as OpenAI's GPT-4, Google's Bard or Meta's LLaMa,
have created unprecedented opportunities for analysing and generating language data on a …

Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation

EC Stade, SW Stirman, LH Ungar, CL Boland… - NPJ Mental Health …, 2024 - nature.com
Large language models (LLMs) such as Open AI's GPT-4 (which power ChatGPT) and
Google's Gemini, built on artificial intelligence, hold immense potential to support, augment …

[PDF][PDF] Can large language models transform computational social science?

C Ziems, W Held, O Shaikh, J Chen, Z Zhang… - Computational …, 2024 - direct.mit.edu
Large language models (LLMs) are capable of successfully performing many language
processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify …

Facilitating self-guided mental health interventions through human-language model interaction: A case study of cognitive restructuring

A Sharma, K Rushton, IW Lin, T Nguyen… - Proceedings of the 2024 …, 2024 - dl.acm.org
Self-guided mental health interventions, such as “do-it-yourself” tools to learn and practice
co** strategies, show great promise to improve access to mental health care. However …

Cognitive reframing of negative thoughts through human-language model interaction

A Sharma, K Rushton, IW Lin, D Wadden… - ar** the helper: Supporting peer counselors via ai-empowered practice and feedback
SL Hsu, RS Shah, P Senthil, Z Ashktorab… - arxiv preprint arxiv …, 2023 - arxiv.org
Millions of users come to online peer counseling platforms to seek support on diverse topics
ranging from relationship stress to anxiety. However, studies show that online peer support …

Building trustworthy NeuroSymbolic AI Systems: Consistency, reliability, explainability, and safety

M Gaur, A Sheth - AI Magazine, 2024 - Wiley Online Library
Explainability and Safety engender trust. These require a model to exhibit consistency and
reliability. To achieve these, it is necessary to use and analyze data and knowledge with …

Imbue: Improving interpersonal effectiveness through simulation and just-in-time feedback with human-language model interaction

IW Lin, A Sharma, CM Rytting, AS Miner, J Suh… - arxiv preprint arxiv …, 2024 - arxiv.org
Navigating certain communication situations can be challenging due to individuals' lack of
skills and the interference of strong emotions. However, effective learning opportunities are …

Multi-level feedback generation with large language models for empowering novice peer counselors

A Chaszczewicz, RS Shah, R Louie, BA Arnow… - arxiv preprint arxiv …, 2024 - arxiv.org
Realistic practice and tailored feedback are key processes for training peer counselors with
clinical skills. However, existing mechanisms of providing feedback largely rely on human …