Pinned Loading

1. ToolQA ToolQA Public

   ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

   Jupyter Notebook 278 12

2. wshi83/EhrAgent wshi83/EhrAgent Public

   [EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

   Python 109 16

3. HYDRA HYDRA Public

   Official Code Repository for paper "HYDRA: Model Factorization Framework for Black-Box LLM Personalization"

   Python 11

4. wshi83/MedAgentGym wshi83/MedAgentGym Public

   [arxiv'25] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

   Python 60 3

5. MLE-Dojo/MLE-Dojo MLE-Dojo/MLE-Dojo Public

   Python 74 3

6. DyGen DyGen Public

   [KDD'23] This is the code repo for our KDD'23 paper "DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling".

   11 1