Evaluation tools for Retrieval-augmented Generation (RAG) methods.

Home of the SanityHarness Leaderboard website.

The official repository for the dataset FactualBench, which is introduced in paper "Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization".

A Flask-Celery integration template for distributed task processing with progress tracking and use MMMLU to evaluation example.

An AI-powered application that provides different reviews of users' playlists across various platforms.

A Python toolkit for the robust evaluation and analysis of seizure detection models.

Multi-class classification of news articles using NLP techniques, TF-IDF, and Naive Bayes

R package for multiplicity-adjusted bootstrap tilting confidence limits for prediction performance after model selection

Automated fish species classification using deep learning (CNN + transfer learning). Includes model training, evaluation metrics, and a Streamlit app for real-time predictions.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.