mlsanityData to 14 Oct 2026

DS@GT at eRisk 2025: From prompts to predictions, benchmarking early depression detection with conversational agent based assessments and temporal attention models

arXiv 2507.10958 ↗First posted 15 Jul 2025cs.CLcited by 1

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

This Working Note summarizes the participation of the DS@GT team in two eRisk 2025 challenges. For the Pilot Task on conversational depression detection with large language-models (LLMs), we adopted a prompt-engineering strategy in which diverse LLMs conducted BDI-II-based assessments and produced structured JSON outputs. Because ground-truth labels were unavailable, we evaluated cross-model agreement and internal consistency. Our prompt design methodology aligned model outputs with BDI-II criteria and enabled the analysis of conversational cues that influenced the prediction of symptoms. Our best submission, second on the official leaderboard, achieved DCHR = 0.50, ADODL = 0.89, and ASHR = 0.27.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 3 of its 22 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

3 of 22 references.

References · 3

  1. 2023LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluationcited by 34
  2. 2024PATIENT-Psi: Using Large Language Models to Simulate Patients for Training Mental Health Professionalscited by 21
  3. 2023MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Textscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidance for Conversational Depression Screeningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Snugi-AI-v2 @ eRisk 2026 Task 2: Early Depression Detection via a Learned Stopping Policy with Sustained Confidence Gate
  2. 2025Systematic Evaluation of Machine-Generated Reasoning and PHQ-9 Labeling for Depression Detection Using Large Language Models
  3. 2025Evaluating Large Language Models for Anxiety, Depression, and Stress Detection: Insights into Prompting Strategies and Synthetic Data
  4. 2026Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement
  5. 2025Enhancing Depression Detection with Chain-of-Thought Prompting: From Emotion to Reasoning Using Large Language Models
  6. 2023Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
  7. 2025DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives
  8. 2025SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information