Pinned Loading
-
confidence_scoring
confidence_scoring Publicthe code and data for Self-Reported Confidence paper
Jupyter Notebook
-
MedQA-BBY
MedQA-BBY PublicForked from ParsBench/ParsBench-Medical
MedQA-but-better-yield (MedQA-BBY) is build on top of MedQA dataset but enriched with labels, as well as two correct options and one negative point option, and three 0 point options. The labels inc…
Jupyter Notebook
-
ParsBench/ParsBench-Medical
ParsBench/ParsBench-Medical PublicMedQA-but-better-yield (MedQA-BBY) is build on top of MedQA dataset but enriched with labels, as well as two correct options and one negative point option, and three 0 point options. The labels inc…
-
Evaluating-Prompt-Engineering-Techniques-for-Accuracy-and-Confidence-Elicitation-in-Medical-LLMs
Evaluating-Prompt-Engineering-Techniques-for-Accuracy-and-Confidence-Elicitation-in-Medical-LLMs Publicthe codes for paper "Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs".
Jupyter Notebook
-
youtube_video_summarizer
youtube_video_summarizer PublicA Python CLI tool that summarizes YouTube or local videos using Google Gemini, with smart SQLite caching for fast, repeatable results.
Python 1
If the problem persists, check the GitHub status page or contact support.
