# SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information Source: [SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:27:04.893Z Authors: Xiangyu Zhang, Hexin Liu, Qiquan Zhang, Beena Ahmed, Julien Epps Published: 2025-02-16T02:02:19.000Z ## Abstract Large Language Models (LLMs) have been increasingly adopted for health-related tasks, yet their performance in depression detection remains limited when relying solely on text input. While Retrieval-Augmented Generation (RAG) typically enhances LLM capabilities, our experiments indicate that traditional text-based RAG systems struggle to significantly improve depression detection accuracy. This challenge stems partly from the rich depression-relevant information encoded in acoustic speech patterns information that current text-only approaches fail to capture effectively. To address this limitation, we conduct a systematic analysis of temporal speech patterns, comparing healthy individuals with those experiencing depression. Based on our findings, we introduce Speech Timing-based Retrieval-Augmented Generation, SpeechT-RAG, a novel system that leverages speech timing features for both accurate depression detection and reliable confidence estimation. This integrated approach not only outperforms traditional text-based RAG systems in detection accuracy but also enhances uncertainty quantification through a confidence scoring mechanism that naturally extends from the same temporal features. Our unified framework achieves comparable results to fine-tuned LLMs without additional training while simultaneously addressing the fundamental requirements for both accuracy and trustworthiness in mental health assessment. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Depression Detection on Depression Detection](): Depression Detection; Depression Detection; Mean ECE: 0.0276. - [Depression Detection on DAIC-WOZ (dev)](): Depression Detection; DAIC-WOZ (dev); F1 (avg): 69.2. ## Original sources and implementation [Original paper]() [PDF]()