EternityYW/BiasEval-LLM-MentalHealth
Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models
This project helps mental health professionals and researchers assess and reduce bias in large language models when analyzing mental health text data. It takes raw text inputs, potentially combined with demographic information, and outputs predictions about mental health conditions along with reasoning, highlighting potential biases related to social factors. The primary users are those working with AI in mental healthcare who need to ensure fair and accurate diagnostic support or research analysis.
No commits in the last 6 months.
Use this if you are developing or evaluating AI tools for mental health analysis and need to understand and address how biases related to social factors (like race, gender, religion) might impact their predictions.
Not ideal if you are looking for a pre-built, production-ready diagnostic tool for direct patient use, as this project focuses on bias evaluation and mitigation in models rather than clinical deployment.
Stars
12
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/EternityYW/BiasEval-LLM-MentalHealth"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google-deepmind/long-form-factuality
Benchmarking long-form factuality in large language models. Original code for our paper...
gnai-creator/aletheion-llm-v2
Decoder-only LLM with integrated epistemic tomography. Knows what it doesn't know.
sandylaker/ib-edl
Calibrating LLMs with Information-Theoretic Evidential Deep Learning (ICLR 2025)
nightdessert/Retrieval_Head
open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality
MLD3/steerability
An open-source evaluation framework for measuring LLM steerability.