# INESC-ID @ eRisk 2025: Exploring Fine-Tuned, Similarity-Based, and Prompt-Based Approaches to Depression Symptom Identification

arXiv: https://arxiv.org/abs/2506.02924 · HTML: https://mlsanity.com/paper/2506.02924/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Depression and Self-Harm Risk Assessment in Online Forums](https://mlsanity.com/paper/1709.01848/) (2017)
- [SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions](https://mlsanity.com/paper/1806.05258/) (2018)
- [The relationship between linguistic expression and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study of blog content](https://mlsanity.com/paper/1811.02750/) (2018)

## Built on by (most cited first, 1 of 1)

- [DS@GT-ARC at eRisk 2026 Task 3: Sparse, Semantic, and LLM Reranking for ADHD Symptom Sentences](https://mlsanity.com/paper/2608.03883/) (2026)

## Abstract (arXiv)

In this work, we describe our team's approach to eRisk's 2025 Task 1: Search for Symptoms of Depression. Given a set of sentences and the Beck's Depression Inventory - II (BDI) questionnaire, participants were tasked with submitting up to 1,000 sentences per depression symptom in the BDI, sorted by relevance. Participant submissions were evaluated according to standard Information Retrieval (IR) metrics, including Average Precision (AP) and R-Precision (R-PREC). The provided training data, however, consisted of sentences labeled as to whether a given sentence was relevant or not w.r.t. one of BDI's symptoms. Due to this labeling limitation, we framed our development as a binary classification task for each BDI symptom, and evaluated accordingly. To that end, we split the available labeled data into training and validation sets, and explored foundation model fine-tuning, sentence similarity, Large Language Model (LLM) prompting, and ensemble techniques. The validation results revealed that fine-tuning foundation models yielded the best performance, particularly when enhanced with synthetic data to mitigate class imbalance. We also observed that the optimal approach varied by symptom. Based on these insights, we devised five independent test runs, two of which used ensemble methods. These runs achieved the highest scores in the official IR evaluation, outperforming submissions from 16 other teams.