Metraipolis › archive › dc_29eee02a3bbc

Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning — arXiv:2609.00605

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00605
License (as archived): CC0-1.0
Archived: 2026-10-17T06:33:32.605Z
SHA-256 of the archived text: 06b2e4b07332276db4ba9f38644639253801264f99830c5e6aab8e4e5c745800
Stable URL of this page: https://metraipolis.com/documento/dc_29eee02a3bbc

How to cite

Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning — arXiv:2609.00605 — arXiv (en), https://arxiv.org/abs/2609.00605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29eee02a3bbc (Metraipolis archive dc_29eee02a3bbc, sha256 06b2e4b07332276db4ba9f38644639253801264f99830c5e6aab8e4e5c745800)

BibTeX

@misc{dc29eee02a3bbc,
  title = {Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning — arXiv:2609.00605},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00605},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29eee02a3bbc; sha256 06b2e4b07332276db4ba9f38644639253801264f99830c5e6aab8e4e5c745800},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic privacy settings where the original training data is inaccessible. We term this gap forget-set misalignment and identify two cases. In Under Unlearning, the forget set omits memorized information and leakage persists. In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility. Using gradient-level analysis, we show these behaviors arise from misaligned unlearning targets rather than specific optimization choices. We then propose CONfession-to-Forget-Set (CONFS), a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge. Across synthetic, multimodal, and real-world benchmarks, CONFS approaches Gold-standard performance on several metrics and achieves a competitive forgetting-utility balance, while preserving utility better than other data-blind forget-set constructions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.00605 — 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 2026-10-17T06:15:12.806Z 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).