Mental disorders present significant challenges to healthcare systems and carry profound social consequences. The rapid development of large language model (LLM) has opened new avenues for enhancing mental healthcare. However, existing approaches primarily rely on instruction tuning and few-shot in-context learning with massive datasets and large-scale backbone models, resulting in significant computational costs. To address these challenges, we propose MentalQLM, a novel lightweight LLM by developing a new dual Low-rank Adaptation (LoRA) approach. The development of MentalQLM consists of two key stages. Firstly, datasets are pruned based on perplexity and diversity analysis to reduce computational requirements. The first LoRA module is instruction-tuned to adapt the LLM for downstream mental health classification tasks. Secondly, a dense layer augmented with a second LoRA module is fine-tuned to enhance performance on complex multi-class classification tasks. Extensive experiments validate the effectiveness of the proposed MentalQLM on five benchmark datasets. Despite having only 0.5B parameters, the model outperforms or demonstrates comparable performance to larger counterparts in both classification and reasoning tasks. This establishes MentalQLM as a promising solution for lightweight and efficient deployment in real-world mental healthcare applications. All the code will be released at https://github.com/tortorish/MentalQLM.

The authors have declared no competing interest.

the National Natural Science Foundation of China (#81903397)

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

All data produced in the present work are contained in the manuscript