Citing mllm-shap¶
If you use mllm-shap in research, please cite the software. The repository’s
CITATION.cff is
the source of truth; GitHub’s “Cite this repository” button renders it as APA or
BibTeX.
BibTeX¶
@software{pozorski_mllm_shap,
author = {Pozorski, Paweł},
title = {mllm-shap: Shapley-value explainability for conversational
language models},
url = {https://github.com/Pawlo77/MLLM-SHAP},
license = {Apache-2.0},
note = {Python package, version as used in your work}
}
Add the version field with the release you used
(python -c "import mllm_shap; print(mllm_shap.__version__)") and record the run
manifest of each reported result, which pins the estimand, estimator, value
function and model.
Citation File Format¶
cff-version: 1.2.0
message: "If you use this work in research, please cite it."
title: "mllm-shap: Shapley-value explainability for conversational language models"
type: software
authors:
- family-names: "Pozorski"
given-names: "Paweł"
email: "pozorski.paul@gmail.com"
version: 0.6.0
date-released: "2026-10-12"
license: Apache-2.0
repository-code: "https://github.com/Pawlo77/MLLM-SHAP"
url: "https://pawlo77.github.io/MLLM-SHAP/"
keywords: [explainability, shapley-value, nlp, llm, xai]
Methods¶
Please also cite the methods your results depend on. The theory pages list the original references:
Shapley value and axioms: Shapley values and axioms
Banzhaf index and estimand choice: Estimands: Shapley vs Banzhaf
Sampling estimators (Monte Carlo, complementary contributions, Neyman allocation): Approximate estimation