Metraipolis › archive › dc_f31468edd6f8

FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software — arXiv:2609.16321

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16321
License (as archived)
CC0-1.0
Archived
2026-10-15T18:34:51.390Z
SHA-256 of the archived text
5c66f52b5e836afd721380a6aecbe78c7c3707d1988a72c006433dec9cdd3257
Stable URL of this page
https://metraipolis.com/documento/dc_f31468edd6f8

How to cite

FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software — arXiv:2609.16321 — arXiv (en), https://arxiv.org/abs/2609.16321 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f31468edd6f8 (Metraipolis archive dc_f31468edd6f8, sha256 5c66f52b5e836afd721380a6aecbe78c7c3707d1988a72c006433dec9cdd3257)
BibTeX
@misc{dcf31468edd6f8,
  title = {FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software — arXiv:2609.16321},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16321},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f31468edd6f8; sha256 5c66f52b5e836afd721380a6aecbe78c7c3707d1988a72c006433dec9cdd3257},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16321. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model development lifecycle before assessing bias. We present FairLint-DL, a Visual Studio Code extension that implements a shift-left approach to fairness testing by enabling pre-training, IDE-native bias detection directly on tabular datasets. FairLint-DL trains a configurable deep neural network as a proxy model and applies information-theoretic Quantitative Individual Discrimination (QID) metrics. Grounded in Shannon and min-entropy, QID quantifies the causal influence of protected attributes on predictions. The system implements a two-phase gradient-guided search algorithm for discovering discriminatory instances, a causal debugging pipeline that localizes bias to specific network layers and neurons via sensitivity analysis, and dual explainability engines using SHAP and LIME for feature-level attribution. Evaluation on three tabular benchmarks (Adult Census Income, German Credit, and Bank Marketing) reveals fairness concerns that vary widely across datasets: on Adult, 96.0% of analyzed instances exhibit QID above the 0.1-bit significance threshold, with a mean QID of 0.619 bits and a disparate impact ratio of 0.581, violating the four-fifths legal rule. FairLint-DL produces these results within 12 seconds on cached models, demonstrating the feasibility of integrating fairness analysis into the developer workflow without significant overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16321 — 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 2026-10-15T18:03:09.619Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).