{"arxiv_id":"2303.15727","incoming":{"papers":35,"sentences":55,"groups":[{"kind":"method_or_tool","label":"Uses its method or tool","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2406.08183","title":"Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Prediction","url":"/paper/2406.08183","section":"Large Language Models","sentence":"We used the python OpenAI library to invoke the Chat Complete API of ChatGPT by using gpt-3.5-turbo backend as in [ref] .","intent_p":1.0,"contests_p":null}]},{"kind":"data_used","label":"Uses its data or values","papers":1,"sentences":1,"quotes":[{"arxiv_id":"2312.04578","title":"Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects","url":"/paper/2312.04578","section":"Task-specific evaluations in psychology","sentence":"Lamichhane's study evaluate the performance of LLM-based ChatGPT in various mental health classification tasks, reporting F1 scores of 0.73 for stress detection, 0.86 for depression detection, and 0.37 for suicidality detection [ref] .","intent_p":0.99,"contests_p":null}]},{"kind":"supports_this_paper","label":"Cites it as support","papers":1,"sentences":2,"quotes":[{"arxiv_id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","url":"/paper/2304.14670","section":"Few-shot Prompting","sentence":"The manual prompt-based approach has shown typical few-shot prompting capabilities in the medical text translation, text augmentation, generation, summarization, and other tasks, with significant improvements over baseline models on public datasets [ref] .","intent_p":0.98,"contests_p":null}]},{"kind":"background","label":"Cites it as background","papers":9,"sentences":11,"quotes":[{"arxiv_id":"2307.14385","title":"Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data","url":"/paper/2307.14385","section":"LLM and Health Applications","sentence":"Closer to our study, Lamichhane [ref] and Amin [ref] tested the performance of ChatGPT (GPT-3.5) on multiple classification tasks (stress, depression, and suicide detection).","intent_p":0.83,"contests_p":null},{"arxiv_id":"2406.08183","title":"Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Prediction","url":"/paper/2406.08183","section":"LLMs for Mental Health Applications","sentence":"Lamichhane et al. [ref] have evaluated the use of ChatGPT (gpt-3.5) to accomplish three mental health-related classification tasks, namely stress detection, depression detection, and suicidal detection.","intent_p":0.87,"contests_p":null},{"arxiv_id":"2606.13176","title":"Mental-R1: Aligning LLM Reasoning for Mental Health Assessment","url":"/paper/2606.13176","section":"Mental Health Assessment","sentence":"Recent studies have applied large language models (LLMs) to mental health assessment, marking a shift from task-specific classifiers toward general-purpose models capable of handling multiple mental health tasks within a unified framework [ref] .","intent_p":0.9,"contests_p":null},{"arxiv_id":"2404.01358","title":"Utilizing AI and Social Media Analytics to Discover Adverse Side Effects of GLP-1 Receptor Agonists","url":"/paper/2404.01358","section":"Introduction","sentence":"It has been widely used in various scientific domains, including mental health research [ref] , medical research [ref] , and detecting drug interactions [ref] .","intent_p":0.83,"contests_p":null},{"arxiv_id":"2312.08299","title":"Conceptualizing Suicidal Behavior: Utilizing Explanations of Predicted Outcomes to Analyze Longitudinal Social Media Data","url":"/paper/2312.08299","section":"Social Media Data Analysis for Mental Health Care","sentence":"Researchers offer a starting point for understanding the application of social media data analysis in mental health care and showcase different methodologies, techniques, and insights from analyzing social media data to improve mental health support and intervention [ref] .","intent_p":0.97,"contests_p":null}]}],"unlabelled_sentences":40},"outgoing":{"papers":5,"sentences":5,"groups":[],"unlabelled_sentences":5},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2303.15727"}}