Menta: A Small Language Model for On-Device Mental Health Prediction

• URL: http://arxiv.org/abs/2512.02716v2
• Date: Wed, 03 Dec 2025 03:43:17 GMT
• Title: Menta: A Small Language Model for On-Device Mental Health Prediction
• Authors: Tianyi Zhang, Xiangyuan Xue, Lingyan Ruan, Shiya Fu, Feng Xia, Simon D'Alfonso, Vassilis Kostakos, Ting Dang, Hong Jia,
• Abstract summary: We introduce Menta, the first optimized SLM fine-tuned specifically for multi-task mental health prediction from social media data.<n>Menta is jointly trained across six classification tasks using a LoRA-based framework, a cross-dataset strategy, and a balanced accuracy--oriented loss.<n>We demonstrate real-time, on-device deployment of Menta on an iPhone 15 Pro Max, requiring only approximately 3GB RAM.
• Score: 19.94525754933305
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mental health conditions affect hundreds of millions globally, yet early detection remains limited. While large language models (LLMs) have shown promise in mental health applications, their size and computational demands hinder practical deployment. Small language models (SLMs) offer a lightweight alternative, but their use for social media--based mental health prediction remains largely underexplored. In this study, we introduce Menta, the first optimized SLM fine-tuned specifically for multi-task mental health prediction from social media data. Menta is jointly trained across six classification tasks using a LoRA-based framework, a cross-dataset strategy, and a balanced accuracy--oriented loss. Evaluated against nine state-of-the-art SLM baselines, Menta achieves an average improvement of 15.2\% across tasks covering depression, stress, and suicidality compared with the best-performing non--fine-tuned SLMs. It also achieves higher accuracy on depression and stress classification tasks compared to 13B-parameter LLMs, while being approximately 3.25x smaller. Moreover, we demonstrate real-time, on-device deployment of Menta on an iPhone 15 Pro Max, requiring only approximately 3GB RAM. Supported by a comprehensive benchmark against existing SLMs and LLMs, Menta highlights the potential for scalable, privacy-preserving mental health monitoring. Code is available at: https://xxue752-nz.github.io/menta-project/

Related papers

• Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation [66.84286617519258]
  Large language models are transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis.<n>Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I (false positive), Type II (false negative), Type S (wrong sign), or Type M (exaggerated effect) errors.<n>We find that intentional LLM hacking is strikingly simple. By replicating 37 data annotation tasks from 21 published social science studies, we show that, with just a handful of prompt paraphrases, virtually anything can be presented as statistically significant.
  arXiv  Detail & Related papers  (2025-09-10T17:58:53Z)
• Beyond Scale: Small Language Models are Comparable to GPT-4 in Mental Health Understanding [12.703061322251093]
  Small Language Models (SLMs) are privacy-preserving alternatives to Large Language Models (LLMs)<n>This paper investigates the mental health understanding capabilities of current SLMs through systematic evaluation across classification tasks.<n>Our work highlights the potential of SLMs in mental health understanding, showing they can be effective privacy-preserving tools for analyzing sensitive online text data.
  arXiv  Detail & Related papers  (2025-07-09T02:40:02Z)
• LlaMADRS: Prompting Large Language Models for Interview-Based Depression Assessment [75.44934940580112]
  This study introduces LlaMADRS, a novel framework leveraging open-source Large Language Models (LLMs) to automate depression severity assessment.<n>We employ a zero-shot prompting strategy with carefully designed cues to guide the model in interpreting and scoring transcribed clinical interviews.<n>Our approach, tested on 236 real-world interviews, demonstrates strong correlations with clinician assessments.
  arXiv  Detail & Related papers  (2025-01-07T08:49:04Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media [31.752563319585196]
  Black box models are inflexible when switching between tasks, and their results typically lack explanations. With the rise of large language models (LLMs), their flexibility has introduced new approaches to the field. In this paper, we introduce the first multi-task Chinese Social Media Interpretable Mental Health Instructions dataset, consisting of 9K samples. We also propose MentalGLM series models, the first open-source LLMs designed for explainable mental health analysis targeting Chinese social media.
  arXiv  Detail & Related papers  (2024-10-14T09:29:27Z)
• mhGPT: A Lightweight Generative Pre-Trained Transformer for Mental Health Text Analysis [8.654701704101779]
  This paper introduces mhGPT, a lightweight generative pre-trained transformer trained on mental health-related social media and PubMed articles. mhGPT was evaluated under limited hardware constraints and compared with state-of-the-art models like MentaLLaMA and Gemma.
  arXiv  Detail & Related papers  (2024-08-15T17:01:57Z)
• ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models [67.97667465509504]
  We develop a novel predictor called ShadowLLM, which can shadow the LLM behavior and enforce better sparsity patterns. ShadowLLM achieves up to a 20% speed-up over the state-of-the-art DejaVu framework.
  arXiv  Detail & Related papers  (2024-06-24T13:41:08Z)
• MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models [28.62967557368565]
  We build the first multi-task and multi-source interpretable mental health instruction dataset on social media, with 105K data samples. We use expert-written few-shot prompts and collected labels to prompt ChatGPT and obtain explanations from its responses. Based on the IMHI dataset and LLaMA2 foundation models, we train MentalLLaMA, the first open-source LLM series for interpretable mental health analysis.
  arXiv  Detail & Related papers  (2023-09-24T06:46:08Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data [42.965788205842465]
  We present a comprehensive evaluation of multiple large language models (LLMs) on various mental health prediction tasks. We conduct experiments covering zero-shot prompting, few-shot prompting, and instruction fine-tuning. Our best-finetuned models, Mental-Alpaca and Mental-FLAN-T5, outperform the best prompt design of GPT-3.5 by 10.9% on balanced accuracy and the best of GPT-4 (250 and 150 times bigger) by 4.8%.
  arXiv  Detail & Related papers  (2023-07-26T06:00:50Z)
• nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales [65.01417261415833]
  We present an approach to predict the pre-training loss based on our observations that Maximal Update Parametrization (muP) enables accurate fitting of scaling laws. With around 14% of the one-time pre-training cost, we can accurately forecast the loss for models up to 52B. Our goal with nanoLM is to empower researchers with limited resources to reach meaningful conclusions on large models.
  arXiv  Detail & Related papers  (2023-04-14T00:45:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.