Metadata-Version: 2.4
Name: boostedprob
Version: 0.1.1
Summary: Utilities to identify dominant tokens and compute boosted model probabilities for Quality Estimation.
Author-email: Tu Anh Dinh <dinhtuanh23@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/TuAnh23/boostedprob
Project-URL: Repository, https://github.com/TuAnh23/boostedprob
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.0.1
Dynamic: license-file

# 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](https://arxiv.org/abs/2502.11115) (EMNLP 2025 Main).

## Install

From PyPI (recommended):
```bash
pip install boostedprob
```

From GitHub (latest development version):
```bash
pip install "git+https://github.com/TuAnh23/boostedprob.git"
```

Or install locally in editable mode:

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

## Examples

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