Metraipolis › archive › dc_69f034f31710

AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising — arXiv:2611.00822

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00822
License (as archived)
CC0-1.0
Archived
2026-11-03T10:31:37.149Z
SHA-256 of the archived text
ab39e9c4b45946254956230cdd6125c0e8266d3cc8deac7eebf727f070a2228c
Stable URL of this page
https://metraipolis.com/documento/dc_69f034f31710

How to cite

AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising — arXiv:2611.00822 — arXiv (en), https://arxiv.org/abs/2611.00822 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69f034f31710 (Metraipolis archive dc_69f034f31710, sha256 ab39e9c4b45946254956230cdd6125c0e8266d3cc8deac7eebf727f070a2228c)
BibTeX
@misc{dc69f034f31710,
  title = {AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising — arXiv:2611.00822},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00822},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69f034f31710; sha256 ab39e9c4b45946254956230cdd6125c0e8266d3cc8deac7eebf727f070a2228c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00822. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM)-native advertising has emerged as a viable monetization channel as LLM service providers seek sustainable revenue streams. However, integrating native ads into LLM responses introduces two largely understudied challenges: (1) controlling ad intensity -- how prominently advertising content appears -- and (2) ad labeling -- identifying which segments of the generated text constitute advertising. We propose AdKnob, a framework jointly addressing both challenges. For ad intensity control, we introduce new ad control tokens without pretrained semantic associations and align the model via direct preference optimization to generate ads at each desired level. For ad labeling, we propose an attention rollout-based attribution mechanism that identifies ad segments by tracing their attribution to input ad-related tokens, requiring no additional inference cost. We further construct MI-KnobSet, the first multi-level ad intensity preference dataset for LLM-native ads. Experiments across six LLMs and human evaluations show that AdKnob achieves uniformly spaced ad intensities where baselines collapse to a narrow range, achieves the highest ad labeling accuracy while being over 500x faster than the strongest baseline, and is preferred over baselines by human evaluators up to 89.6% of the time.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00822 — 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 2026-11-03T10:29:48.483Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).