Skip to content

LabARSS/question-complextiy-estimation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

phi-4

This repo contains code for the paper "When an LLM is apprehensive about its answers - and when its uncertainty is justified".

How to run

  • MASJ and entropy notebooks can be found in notebooks by prefixes estimate_entropy_... and model_as_judge_...;
  • Source data is in data;
  • Analytics is in notebooks under the prefix analysis_....

Citation

@article{llmuncertainty,
title        = {When an LLM is apprehensive about its answers - and when its uncertainty is justified},
author       = {Petr Sychev and Andrey Goncharov and Daniil Vyazhev and Edvard Khalafyan and Alexey Zaytsev},
howpublished = {https://arxiv.org/abs/2503.01688},
year         = {2025}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published