Metraipolis › archive › dc_ba476569dc91

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds — arXiv:2608.26743

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26743
License (as archived)
CC0-1.0
Archived
2026-10-17T14:22:54.590Z
SHA-256 of the archived text
a1773b3fd23041cc440813bc721fca1964d8355ef5d834f4a3639149b07acf93
Stable URL of this page
https://metraipolis.com/documento/dc_ba476569dc91

How to cite

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds — arXiv:2608.26743 — arXiv (en), https://arxiv.org/abs/2608.26743 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba476569dc91 (Metraipolis archive dc_ba476569dc91, sha256 a1773b3fd23041cc440813bc721fca1964d8355ef5d834f4a3639149b07acf93)
BibTeX
@misc{dcba476569dc91,
  title = {Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds — arXiv:2608.26743},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26743},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba476569dc91; sha256 a1773b3fd23041cc440813bc721fca1964d8355ef5d834f4a3639149b07acf93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26743. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes requested knowledge while preserving model utility, offering a practical alternative to full retraining, but existing methods treat the explicitly identified forget examples as the complete deletion scope. This is insufficient when target knowledge remains recoverable through paraphrases, aliases, or neighboring training examples. We propose GRAPHSU, a graph-guided controller that expands the deletion scope beyond forget seeds by constructing a weighted support-route graph, propagating deletion pressure through it, and applying graded forgetting strengths to high-risk neighbors. On the Task of Fictitious Unlearning (TOFU), a synthetic author-profile question-answering benchmark, and PISTOL, a structural-unlearning benchmark built around interconnected factual samples, with GPT-2 Medium and Llama-3.2-3B-Instruct, GRAPHSU achieves the lowest utility-feasible soft leakage across all deletion settings, reducing leakage by up to 49.5 percentage points over a matched seed-only baseline, demonstrating that effective enterprise unlearning requires controlling support routes, not just forget seeds.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26743 — 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 2026-10-17T13:16:53.514Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).