Skip to content

This repository hosts the paper “LLM Based Math Tutoring: Challenges and Dataset”, along with the accompanying dataset. It explores the performance and challenges of Large Language Models (LLMs) in math tutoring scenarios, providing a benchmark dataset for evaluating LLM accuracy in educational contexts.

License

Notifications You must be signed in to change notification settings

Khan/tutoring-accuracy-dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Evaluation Dataset License; Conditions of Use
Copyright© 2024 Khan Academy, Inc.  
 
Subject to the terms and conditions of this Evaluation Dataset License, Khan Academy hereby grants, free of charge, to each person obtaining a copy of this dataset and any associated documentation files from an authorized source (the "Dataset"), permission to use the Dataset internally, solely for purposes of evaluating artificial intelligence models, including large language models.  This includes, without limitation, the rights to use, copy, modify, merge, or combine with other data, and to allow other authorized users within the same entity to do so.  The foregoing license is subject to the following conditions:
 
1.  USE RESTRICTION: Use of the Dataset shall be restricted to internal non-commercial evaluation  of models. Any other use or exploitation (including any re-distribution or publication, use for model training, or any production use) of the Dataset or its derivatives is expressly prohibited.
2. NO SUBLICENSE RIGHTS: This license is not sublicensable and does not grant the recipient any rights to further license or sublicense the Dataset to another party, beyond the limited right to allow authorized users within the same entity to exercise the license.
3.  NO COMMERCIAL EXPLOITATION: Direct or indirect sale, lease, or commercial exploitation of the Dataset or its derivatives is prohibited. For the avoidance of doubt, the foregoing restriction does not prohibit (i) use of the Dataset in connection with evaluation of products intended for commercial use or exploitation, or (ii) commercial use of insights and learnings gained from permitted evaluations.
4.  COMBINATIONS.  Notwithstanding the rights granted to modify, merge, or combine the Dataset with other data, any such modified, merged, or combined dataset containing any portion of the Dataset remains subject to this license, including these restrictions.
 
The above copyright notice and this permission and list of conditions notice shall be included in all copies or substantial portions of the Dataset.
 
DISCLAIMER: THE DATASET IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE DATASET OR THE USE OR OTHER DEALINGS IN THE DATASET, INCLUDING ANY CLAIM WITH RESPECT TO ANY SEPARATE MODEL, SYSTEM, PRODUCT OR SERVICE THE DATASET MAY BE USED IN CONJUNCTION WITH.

About

This repository hosts the paper “LLM Based Math Tutoring: Challenges and Dataset”, along with the accompanying dataset. It explores the performance and challenges of Large Language Models (LLMs) in math tutoring scenarios, providing a benchmark dataset for evaluating LLM accuracy in educational contexts.

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published