# Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches

arXiv: https://arxiv.org/abs/2509.25795 · HTML: https://mlsanity.com/paper/2509.25795/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 55 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare](https://mlsanity.com/paper/2110.15621/) (2021)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models](https://mlsanity.com/paper/2309.13567/) (2023)
- [Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Model](https://mlsanity.com/paper/2202.08210/) (2022)
- [Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences](https://mlsanity.com/paper/1804.07000/) (2018)
- [Gender Bias in Depression Detection Using Audio Features](https://mlsanity.com/paper/2010.15120/) (2020)
- [Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media](https://mlsanity.com/paper/2305.05138/) (2023)
- [Does GPT-4 surpass human performance in linguistic pragmatics?](https://mlsanity.com/paper/2312.09545/) (2023)
- [Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models](https://mlsanity.com/paper/2406.12033/) (2024)
- [Advancing Depression Detection on Social Media Platforms Through Fine-Tuned Large Language Models](https://mlsanity.com/paper/2409.14794/) (2024)

## Built on by (most cited first, 2 of 2)

- [Investigating Associational Biases in Inter-Model Communication of Large Generative Models](https://mlsanity.com/paper/2601.22093/) (2026)
- [When Symptoms Are Not Enough: Evidence-Weighting Patterns in Large Language Model Psychiatric Screening](https://mlsanity.com/paper/2605.23148/) (2026)

## Abstract (arXiv)

This paper investigates algorithmic bias in language-based models for automated depression detection, focusing on socio-demographic disparities related to gender and race/ethnicity. Models trained using deep neural networks (DNN) based embeddings are compared to few-shot learning approaches with large language models (LLMs), evaluating both performance and fairness on clinical interview transcripts from the Distress Analysis Interview Corpus/Wizard-of-Oz (DAIC-WOZ). To mitigate bias, fairness-aware loss functions are applied to DNN-based models, while in-context learning with varied prompt framing and shot counts is explored for LLMs. Results indicate that LLMs outperform DNN-based models in depression classification, particularly for underrepresented groups such as Hispanic participants. LLMs also exhibit reduced gender bias compared to DNN-based embeddings, though racial disparities persist. Among fairness-aware techniques for mitigating bias in DNN-based embeddings, the worst-group loss, which is designed to minimize loss for the worst-performing demographic group, achieves a better balance between performance and fairness. In contrast, the fairness-regularized loss minimizes loss across all groups but performs less effectively. In LLMs, guided prompting with ethical framing helps mitigate gender bias in the 1-shot setting. However, increasing the number of shots does not lead to further reductions in disparities. For race/ethnicity, neither prompting strategy nor increasing N in N-shot learning effectively reduces disparities.