Metraipolis › archive › dc_f458d5dfe735

SCM-based Fairness and Faithful Explainability for Legal Document Classification — arXiv:2610.00045

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00045
License (as archived)
CC0-1.0
Archived
2026-10-06T13:53:31.421Z
SHA-256 of the archived text
ca232f44942f7fbf3c633d26624effd4b1858cd37187290fae7d4b20f624cef4
Stable URL of this page
https://metraipolis.com/documento/dc_f458d5dfe735

How to cite

SCM-based Fairness and Faithful Explainability for Legal Document Classification — arXiv:2610.00045 — arXiv (en), https://arxiv.org/abs/2610.00045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f458d5dfe735 (Metraipolis archive dc_f458d5dfe735, sha256 ca232f44942f7fbf3c633d26624effd4b1858cd37187290fae7d4b20f624cef4)
BibTeX
@misc{dcf458d5dfe735,
  title = {SCM-based Fairness and Faithful Explainability for Legal Document Classification — arXiv:2610.00045},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00045},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f458d5dfe735; sha256 ca232f44942f7fbf3c633d26624effd4b1858cd37187290fae7d4b20f624cef4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transformer models such as LegalBERT are increasingly used in legal decision support, raising concerns about both fairness and the transparency of model explanations. These properties are usually evaluated separately, leaving open whether a debiasing intervention that changes fairness also changes how faithfully explanations reflect model reasoning. This study investigates that relationship on the ECtHR alleged-violations corpus from LexGLUE. It compares a LegalBERT baseline with a fairness-regularized variant that penalizes stereotypical warmth and competence representations during fine-tuning. The evaluation covers predictive performance, demographic fairness, and SHAP explanation faithfulness across five random seeds. At the performance-optimal regularization strength, the intervention does not reduce demographic disparity. This null result holds across two fairness definitions and a conventional word-pair control on the gender axis. Classification performance is largely unchanged. However, the intervention consistently degrades explanation sufficiency across all five seeds and three thresholds. A shuffled-pair control reproduces this degradation while leaving performance and fairness unchanged, indicating that the effect arises from contrastive representational regularization rather than specifically from the warmth and competence structure. The results demonstrate a dissociation between fairness and explanation faithfulness: changes in explanation behavior do not necessarily indicate changes in fairness, and fairness must therefore be evaluated directly.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.00045 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T12:15:34.594Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).