mlsanityData to 14 Oct 2026

A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG

arXiv 2503.24307 ↗First posted 31 Mar 2025cs.CL cs.AI cs.IRcited by 15

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

This study presents a systematic comparison of three approaches for the analysis of mental health text using large language models (LLMs): prompt engineering, retrieval augmented generation (RAG), and fine-tuning. Using LLaMA 3, we evaluate these approaches on emotion classification and mental health condition detection tasks across two datasets. Fine-tuning achieves the highest accuracy (91% for emotion classification, 80% for mental health conditions) but requires substantial computational resources and large training sets, while prompt engineering and RAG offer more flexible deployment with moderate performance (40-68% accuracy). Our findings provide practical insights for implementing LLM-based solutions in mental health applications, highlighting the trade-offs between accuracy, computational requirements, and deployment flexibility.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 12 of its 27 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

12 of 27 references.

References · 12

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  8. 2023A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethicscited by 163
  9. 2023Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Codingcited by 82
  10. 2023Evaluation of ChatGPT for NLP-based Mental Health Applicationscited by 53
  11. 2020Suicidal Ideation and Mental Disorder Detection with Attentive Relation Networkscited by 28
  12. 2024Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Taskscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 8.

15 papers.

Sort:

By area:

  1. 2025Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosiscited by 8
  2. 2025Survey and Experiments on Mental Disorder Detection via Social Media: From Large Language Models and RAG to Agentscited by 6
  3. 2025Sanitizing Manufacturing Dataset Labels Using Vision-Language Modelscited by 6
  4. 2025Rule2Text: Natural Language Explanation of Logical Rules in Knowledge Graphscited by 3
  5. 2025Confidence-Credibility Aware Weighted Ensembles of Small LLMs Outperform Large LLMs in Emotion Detectioncited by 1
  6. 2025A Novel Multi-Timescale Stability-Preserving Hierarchical Reinforcement Learning Controller Framework for Adaptive Control in High-Dimensional Dynamical Systemscited by 0
  7. 2025Vision-Language Models for Infrared Industrial Sensing in Additive Manufacturing Scene Descriptioncited by 0
  8. 2026CMHL: Contrastive Multi-Head Learning for Emotionally Consistent Text Classificationcited by 0
  9. 2026From Baselines to Preferences: A Comparative Study of LoRA/QLoRA and Preference Optimization for Mental Health Text Classificationcited by 0
  10. 2026CAMO: A Class-Aware Minority-Optimized Ensemble for Robust Language Model Evaluation on Imbalanced Datacited by 0
  11. 2026DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methodscited by 0
  12. 2026Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessmentcited by 0
3 more
  1. 2026Reading Anxiety or Reading the Label? Comparing Fine-Tuned and Frontier Models for Anxiety Detection on Social Mediacited by 0
  2. 2026Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generationcited by 0
  3. 2026From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Healthcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
  2. 2023Towards Interpretable Mental Health Analysis with Large Language Models
  3. 2026Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture
  4. 2025Evaluating Large Language Models for Anxiety, Depression, and Stress Detection: Insights into Prompting Strategies and Synthetic Data
  5. 2025A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context
  6. 2025Navigating through the hidden embedding space: steering LLMs to improve mental health assessment
  7. 2025Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text
  8. 2026LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback