Metraipolis › archive › dc_0569dfe54cab

Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation — arXiv:2608.26735

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26735
License (as archived)
CC0-1.0
Archived
2026-10-17T15:19:52.577Z
SHA-256 of the archived text
488cd8de4cf119c5231f7bb5796f29076df1abb0409378f000f0571bc740a727
Stable URL of this page
https://metraipolis.com/documento/dc_0569dfe54cab

How to cite

Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation — arXiv:2608.26735 — arXiv (en), https://arxiv.org/abs/2608.26735 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0569dfe54cab (Metraipolis archive dc_0569dfe54cab, sha256 488cd8de4cf119c5231f7bb5796f29076df1abb0409378f000f0571bc740a727)
BibTeX
@misc{dc0569dfe54cab,
  title = {Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation — arXiv:2608.26735},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26735},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0569dfe54cab; sha256 488cd8de4cf119c5231f7bb5796f29076df1abb0409378f000f0571bc740a727},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26735. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Specializing large language models to vertical domains improves domain-specific behavior but often degrades general capabilities. We study this trade-off in Multi-Teacher On-Policy Distillation (MOPD), where a specialized model learns from domain and general teachers on its own sampled trajectories. Standard MOPD faces two limitations: ordinary on-policy sampling rarely exposes tokens with large positive teacher--student advantages, and advantage sign alone does not establish whether the proposed update direction is reliable. We propose Uncertainty-Calibrated MOPD (UCMOPD), which addresses these limitations through two complementary mechanisms. Golden-Gain Enhancement combines higher-temperature exploration with a standard-temperature anchor and retains trajectories whose positive learning signal matches or exceeds the prompt-specific anchor. Teacher-Endorsement Filtering then uses centered log-likelihood (CLL) to estimate each retained token's plausibility relative to the teacher's uncertainty and probabilistically preserves updates whose directions are supported by that endorsement. Across role-playing and medical-domain specialization, UCMOPD improves the general-capability average over standard MOPD by $4.48\%$ and $7.86\%$, respectively, while maintaining vertical-domain performance. Component ablations and diagnostic analyses support the intended roles of the two mechanisms: exposing and selecting stronger positive signals at the trajectory level and validating update directions through teacher endorsement at the token level.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.26735 — 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 2026-10-17T15:15:18.070Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).