Skip to main content

Utilities to identify dominant tokens and compute boosted model probabilities for Quality Estimation.

Project description

BoostedProb

Implementation of Boosted Model Probability (BoostedProb) for Quality Estimation introduced in the paper: Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability (EMNLP 2025 Main).

Install

From PyPI (recommended):

pip install boostedprob

From GitHub (latest development version):

pip install "git+https://github.com/TuAnh23/boostedprob.git"

Or install locally in editable mode:

git clone https://github.com/TuAnh23/boostedprob.git
cd boostedprob
pip install -e .

Examples

See the examples/ folder for integration with Hugging Face models.

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

boostedprob-0.1.1.tar.gz (4.8 kB view details)

Uploaded Source

Built Distribution

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

boostedprob-0.1.1-py3-none-any.whl (4.7 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: boostedprob-0.1.1.tar.gz
  • Upload date:
  • Size: 4.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for boostedprob-0.1.1.tar.gz
Algorithm Hash digest
SHA256 b1f465fad71e7d7f124e06c897138f627a4d9f175ce9660bf1b09c70efdef4d2
MD5 618f01bd3fa642e2a5612983c7a892a7
BLAKE2b-256 73d0e663b3f4a4c3a612554c7ba573c0362b644be05742eb40bc6d4396e7fc55

See more details on using hashes here.

File details

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

File metadata

  • Download URL: boostedprob-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 4.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.16

File hashes

Hashes for boostedprob-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b1d9c1038eebc841683014c2d0066d3628b8e55efaddabc413d1af6761355984
MD5 9a89224dabeafdf3d78e2f90e9602305
BLAKE2b-256 96ecc50ef10239da09101ec86641fc4d15e0698f31f7f92b89b64097ec6a5db2

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