XAI Embeddings

A Python package for explainable AI (XAI) embeddings analysis, using perturbation based explanation methods for transformer-based models. Explanations show how tokens influence position of each other.

Installation

pip install xaiembeddings

Requirements for POS-PFI

Spacy Model: path to spacy model e.g.: en_core_web_trf
Part-of-speech Dictionary: dictionary with list of words for permutations.

Available Explainers

AttentionExplainer: Uses attention weights to explain token importance
LOOExplainer: Leave-one-out analysis
POSPermutationExplainer: Part-of-speech based permutation analysis
SubsetExplainer: Subset-based explanation generation

Models

BERTModel: BERT bert-base-uncased with embedding extraction
Model: Abstract base class for custom model implementations

Examples:

Sample usage was provided in examples.ipynb

License

This project is licensed under the MIT License.

Metadata

Release files for xaiembeddings 0.1.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for xaiembeddings 0.1.3
File	Size	Uploaded	Provenance	Actions
xaiembeddings-0.1.3.tar.gz	2.0 MB	Sep 27, 2025	Without provenance	Details for xaiembeddings-0.1.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for xaiembeddings 0.1.3
File	Interpreter	ABI	Platform	Actions Reset
xaiembeddings-0.1.3-py3-none-any.whl 17.3 kB Sep 27, 2025 Without provenance	Python 3	none	any	Details for xaiembeddings-0.1.3-py3-none-any.whl

Total release size: 2.0 MB

Release files / xaiembeddings-0.1.3.tar.gz

Download URL	xaiembeddings-0.1.3.tar.gz
Size	2.0 MB
Tags	Source
SHA-256 checksum How to use checksums	`94da35befea4c14e6753d12d2d36b234a78864cde000c8857918e5cedd984df6`
BLAKE2b-256 checksum How to use checksums	`df455ada0c505a96fcd554988dfd19f576a35fd51ec26e0875bd5647fff4a0d5`
Upload date	Sep 27, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.13.7`

Release files / xaiembeddings-0.1.3-py3-none-any.whl

Download URL	xaiembeddings-0.1.3-py3-none-any.whl
Size	17.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`8d036a1ccf06a8955c8518c8522afbc895cec16df46aecd12374a38721e317fa`
BLAKE2b-256 checksum How to use checksums	`4f1785e39b4fa441c65ee4e8598b52f206470bf34a6f843a5206d84adc62d2df`
Upload date	Sep 27, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.13.7`

Security for xaiembeddings 0.1.3

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.3 This release

Sep 27, 2025 2 release files No provenance

0.1.2