Metraipolis › archive › dc_edca007c21e9
LLM unbranding: Erasing Commercial Identity while Preserving Generic Utility — arXiv:2609.37127
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37127
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:56:52.210Z
- SHA-256 of the archived text
a66399284b8aa8b3f7509a43cd1f0deae5e924962fb15bc781cae63af03cb028- Stable URL of this page
https://metraipolis.com/documento/dc_edca007c21e9
How to cite
LLM unbranding: Erasing Commercial Identity while Preserving Generic Utility — arXiv:2609.37127 — arXiv (en), https://arxiv.org/abs/2609.37127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edca007c21e9 (Metraipolis archive dc_edca007c21e9, sha256 a66399284b8aa8b3f7509a43cd1f0deae5e924962fb15bc781cae63af03cb028)
BibTeX
@misc{dcedca007c21e9,
title = {LLM unbranding: Erasing Commercial Identity while Preserving Generic Utility — arXiv:2609.37127},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37127},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edca007c21e9; sha256 a66399284b8aa8b3f7509a43cd1f0deae5e924962fb15bc781cae63af03cb028},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Establishing unbranding as a critical practice to prevent visual logos from acquiring negative connotations is standard in image generation. Large Language Models (LLMs) now face a parallel and emerging challenge. These models frequently generate brand descriptions within diverse contexts. This frequency introduces significant risks, such as trademark dilution, false attribution, and brand defamation. In response, we formally define the novel task of LLM Unbranding. We specifically address the complex challenge of managing trade dress within textual outputs. This involves neutralizing characteristic language, slogans, and stylistic markers that define brand identity. Crucially, these elements are less evident than explicit visual logos. To benchmark this task, we introduce a comprehensive evaluation dataset incorporating prominent brands from multiple commercial domains. We rigorously evaluate existing state-of-the-art machine unlearning models using this benchmark. This evaluation identifies their limitations in selective textual unbranding. Finally, we propose MUTE, a novel inference-time method that effectively neutralizes textual trade dress while preserving the LLM's general capabilities and utility. By leveraging an iterative refinement loop, MUTE systematically optimizes system instructions to safely eliminate brand leakage without requiring fragile parameter updates. Code and dataset: The evaluation dataset and code for LLM Unbranding are available at this https URL . The implementation of MUTE is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.37127 — 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 2026-10-07T16:27:03.278Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).