Metraipolis › archive › dc_9b021e2c97be

Feeling of Knowing in Large Language Models — arXiv:2611.04834

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04834
License (as archived)
CC0-1.0
Archived
2026-11-04T18:35:18.436Z
SHA-256 of the archived text
e9720deab80505e10496c9553f6a516812c2f4d7c5f592b322b59b6732112b49
Stable URL of this page
https://metraipolis.com/documento/dc_9b021e2c97be

How to cite

Feeling of Knowing in Large Language Models — arXiv:2611.04834 — arXiv (en), https://arxiv.org/abs/2611.04834 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b021e2c97be (Metraipolis archive dc_9b021e2c97be, sha256 e9720deab80505e10496c9553f6a516812c2f4d7c5f592b322b59b6732112b49)
BibTeX
@misc{dc9b021e2c97be,
  title = {Feeling of Knowing in Large Language Models — arXiv:2611.04834},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04834},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b021e2c97be; sha256 e9720deab80505e10496c9553f6a516812c2f4d7c5f592b322b59b6732112b49},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04834. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Post-training updates change what large language models (LLMs) can answer, but may leave their answerability judgments misaligned. We study this knowledge-judgment desynchronization through functional feeling of knowing (FoK), which supports selective generation, retrieval triggering, and model routing without implying subjective experience. We propose two trainable channels: a knowledge channel that changes answerability and a FoK channel that judges the current knowledge state. Three stages train them: on-policy supervised fine-tuning (OP-SFT) updates knowledge from corrected on-policy answers; knowledge-delta FoK training (K$\Delta$-FT) adapts judgments across intermediate knowledge states; and FoK-guided policy optimization (FGPO) trains the subsequent answer or explanation. Factual-QA experiments, cross-dataset evaluation, and three sequential updates show that explicit FoK alignment improves judgment quality on updated knowledge. MMLU and ARC-Easy separately assess capability preservation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04834 — 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 2026-11-04T18:32:37.342Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).