https://github.com/deepset-ai/llm_judge_experiments
https://github.com/deepset-ai/llm_judge_experiments
Last synced: 8 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/deepset-ai/llm_judge_experiments
- Owner: deepset-ai
- License: apache-2.0
- Created: 2024-07-11T16:10:58.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-07-11T16:32:42.000Z (over 1 year ago)
- Last Synced: 2025-02-16T02:25:07.559Z (10 months ago)
- Language: Jupyter Notebook
- Size: 3.03 MB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# llm_judge_experiments
This repo contains experiments using LLMs as a Judge.
The following experiments have been run:
- context relevance
The repository is structured as follows:
- data: contains datasets used to evaluate experiments
- notebooks: contains jupyter notebooks used to create and evaluate experiments
For invocation [Haystack v2](https://haystack.deepset.ai/) has been used.
Whenever API tokens or credentials are required, there are INSERT_TOKEN_HERE or similar placeholders in the notebooks.