Metraipolis › archive › dc_18e42a82ee4e

Unifying Conformal Language Tasks with In-Context Ensembles — arXiv:2609.03005

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03005
License (as archived)
CC0-1.0
Archived
2026-10-17T01:39:56.212Z
SHA-256 of the archived text
b56495cead7135aa2114315db445f0b21f7865c8d07e62997423a0820fef946d
Stable URL of this page
https://metraipolis.com/documento/dc_18e42a82ee4e

How to cite

Unifying Conformal Language Tasks with In-Context Ensembles — arXiv:2609.03005 — arXiv (en), https://arxiv.org/abs/2609.03005 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18e42a82ee4e (Metraipolis archive dc_18e42a82ee4e, sha256 b56495cead7135aa2114315db445f0b21f7865c8d07e62997423a0820fef946d)
BibTeX
@misc{dc18e42a82ee4e,
  title = {Unifying Conformal Language Tasks with In-Context Ensembles — arXiv:2609.03005},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03005},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18e42a82ee4e; sha256 b56495cead7135aa2114315db445f0b21f7865c8d07e62997423a0820fef946d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03005. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: coverage, retaining enough pertinent information to achieve some goal, and conciseness, removing as much irrelevant information as possible. Conformal prediction methods have been used to guarantee coverage, and must be optimized for conciseness through design of a score function. State-of-the-art scoring functions use hand-engineered LLM prompts asking the model to rate the importance of content, but manual prompt engineering is labor-intensive and task-specific. We introduce the Conformal Relevance framework which uses in-context learning example curation and ensembling to create a score function which maintains coverage while improving conciseness with minimal manual input. We demonstrate this framework's application on seven NLP tasks, and also theoretically study the impact of diversity for ensembled conformal scores, giving a complementarity condition that characterizes when ensembling improves worst-case sentence scores, and a saturation bound on ensemble improvement.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.03005 — 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 2026-10-17T01:11:43.497Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).