Metraipolis › archive › dc_07a14defbf70

Verb-ICL: Rethinking In-Context Learning for Structured Prediction — arXiv:2610.04725

Source
arXiv
Original
https://arxiv.org/abs/2610.04725
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:09.061Z
SHA-256 of the archived text
fd50f48967bb51c4e561fa53cadbdc94efd4cbd6ee8305ab436d2b2f0ca081b0
Stable URL of this page
https://metraipolis.com/documento/dc_07a14defbf70

How to cite

Verb-ICL: Rethinking In-Context Learning for Structured Prediction — arXiv:2610.04725 — arXiv, https://arxiv.org/abs/2610.04725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07a14defbf70 (Metraipolis archive dc_07a14defbf70, sha256 fd50f48967bb51c4e561fa53cadbdc94efd4cbd6ee8305ab436d2b2f0ca081b0)
BibTeX
@misc{dc07a14defbf70,
  title = {Verb-ICL: Rethinking In-Context Learning for Structured Prediction — arXiv:2610.04725},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07a14defbf70; sha256 fd50f48967bb51c4e561fa53cadbdc94efd4cbd6ee8305ab436d2b2f0ca081b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Structured prediction tasks pose unique challenges for in-context learning (ICL): their compositional outputs require modeling fine-grained, token-level patterns that sentence-level approaches fail to capture, and their task-specific annotation conventions are human-defined artifacts that cannot be acquired through pretraining alone. We propose Verb-ICL, a selective annotation framework for ICL-based structured prediction that addresses both challenges. Verb-ICL first selects representative examples using a token-level coverage strategy that captures local semantic patterns critical for structured prediction, then generates actionable error feedback that codifies task-specific annotation guidelines and incorporates this feedback into ICL demonstrations. We evaluate Verb-ICL on six structured prediction datasets spanning information extraction and semantic parsing. Experiments with recent LLMs show that Verb-ICL consistently outperforms strong selective annotation baselines under low-resource settings and continues to provide gains as the annotation budget increases. Extended analyses demonstrate that the generated feedback is predominantly useful across a four-category quality taxonomy, generalizes as task-level guidance beyond instance-specific corrections, and improves performance regardless of the underlying selection strategy.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.04725 — 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 2026-10-06T05:24:20.280Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).