Metraipolis › archive › dc_a8aead617627

I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models — arXiv:2609.00003

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00003
License (as archived)
CC0-1.0
Archived
2026-10-17T06:31:35.600Z
SHA-256 of the archived text
fac6662d2b94181d961360cca5787103cc9d41efa09dfd44549078cec1e8f106
Stable URL of this page
https://metraipolis.com/documento/dc_a8aead617627

How to cite

I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models — arXiv:2609.00003 — arXiv (en), https://arxiv.org/abs/2609.00003 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a8aead617627 (Metraipolis archive dc_a8aead617627, sha256 fac6662d2b94181d961360cca5787103cc9d41efa09dfd44549078cec1e8f106)
BibTeX
@misc{dca8aead617627,
  title = {I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models — arXiv:2609.00003},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00003},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a8aead617627; sha256 fac6662d2b94181d961360cca5787103cc9d41efa09dfd44549078cec1e8f106},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00003. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearning, the unintended degradation of semantically related concepts that should have been retained (henceforth, interference) remains poorly characterized and inconsistently evaluated. This paper introduces I-CARE, a methodology that formalizes interference as a first-class object of study in generative unlearning. Rather than proposing a new benchmark or unlearning algorithm, I-CARE provides formal definitions for tasks, metrics, and templates for reporting results, enabling the systematic and reproducible study of interference across unlearning settings. While our methodology is designed to remain valid as models and unlearning algorithms evolve, decoupling long-term scientific insight from transient empirical results, we present a feasibility demonstration with state-of-the-art algorithms and frequently used datasets. The results demonstrate that I-CARE enables meaningful analysis of interference patterns across multiple unlearning settings, establishing the practical applicability of the framework. The software implementation of the methodology is provided in an open-source framework, together with a web-based graphical interface that enables exploration of the outcomes of this study without requiring direct interaction with the codebase or specialized data analysis tools.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00003 — 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 2026-10-17T06:15:12.536Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).