Skip to main content

An automatic evaluation package for assessing the quality of LLM-generated multi-document topic sets.

Project description

Tpower5Score

An automatic evaluation package for assessing the quality of LLM-generated multi-document topic sets.

📦 How to install

pip install tpower5score

🚀 How to use

    topics_set = [<topics_set>]
    docs = [<documents>]

    agg_weights = {
        'Interpretability': 0.2,
        'Topic Coverage': 0.2,
        'Document Coverage': 0.2,
        'Overlap': 0.2,
        'Rank': 0.2
    }

    aspects, agg_score = tpower5score.evaluate(topics_set, docs)

Or see working example in examples/main.py

📖 Citation

If you use this package in your work, please cite:

@article{
  title={$T^5Score$: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets},
  author={Trainin Itamar, Omri Abend},
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tpower5score-0.1.1.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

tpower5score-0.1.1-py3-none-any.whl (7.5 kB view details)

Uploaded Python 3

File details

Details for the file tpower5score-0.1.1.tar.gz.

File metadata

  • Download URL: tpower5score-0.1.1.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.2

File hashes

Hashes for tpower5score-0.1.1.tar.gz
Algorithm Hash digest
SHA256 148cb0561f5fc490abf7d720aba83aaaefcab49990cae50c0b6af9bb025f58c3
MD5 239f644657d0ea877ae232bdd5eb0823
BLAKE2b-256 033f7defe8b6f3f1cdd9b051f70291daeb9133a673b61e4e1b849865e2426386

See more details on using hashes here.

File details

Details for the file tpower5score-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: tpower5score-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 7.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.2

File hashes

Hashes for tpower5score-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 72b02e54a930223ff037b193088bd8d30c175f3676d48ffc0f62429e675ab370
MD5 3e8d583f3e382c1188caf1e4f95f7a91
BLAKE2b-256 ec4a28aafc72a65305ecfe7b2d41d87d9c46a03e2712bedec4d0c24d215c3f89

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page