Metraipolis › archive › dc_b73cb079d5af

Finding Errors Is Not Enough: Selective Model Escalation for Entity-Targeted Sentiment Analysis — arXiv:2611.02989

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02989
License (as archived)
CC0-1.0
Archived
2026-11-03T18:23:48.175Z
SHA-256 of the archived text
9e0d6978b909fb68f646c1633244abcdd14ad1a896c94370c81a395cdca39d82
Stable URL of this page
https://metraipolis.com/documento/dc_b73cb079d5af

How to cite

Finding Errors Is Not Enough: Selective Model Escalation for Entity-Targeted Sentiment Analysis — arXiv:2611.02989 — arXiv (en), https://arxiv.org/abs/2611.02989 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b73cb079d5af (Metraipolis archive dc_b73cb079d5af, sha256 9e0d6978b909fb68f646c1633244abcdd14ad1a896c94370c81a395cdca39d82)
BibTeX
@misc{dcb73cb079d5af,
  title = {Finding Errors Is Not Enough: Selective Model Escalation for Entity-Targeted Sentiment Analysis — arXiv:2611.02989},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02989},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b73cb079d5af; sha256 9e0d6978b909fb68f646c1633244abcdd14ad1a896c94370c81a395cdca39d82},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02989. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Improving a sentiment classifier with limited resources involves more than simply deciding how much data to collect or which model to train. A labelled collection may lack examples of an important class. Once trained, a classifier may benefit from another model even when that model is weaker on its own. We study these decisions in document-level Entity-Level Sentiment Analysis (ELSA), primarily using South Slavic news. We first compare acquisition orders as collections grow. We then use uncertainty to choose which predictions to revisit, how many to process, and whether an alternative encoder or local LLM can correct them. Finally, we select complete routing policies on development data for held-out evaluation. Minority-prioritised acquisition helps at some very small training sizes, but not consistently thereafter. On SentiCoref, an oracle correcting all errors in the least-confident 10% without harming correct predictions would add 9.14 Macro-F1 points; however the best evaluated action gains only 0.90. Encoder averaging helps on AspectBench and NewsMTSC but harms SentiCoref, where selective LLM assistance is more promising. Both development-selected policies route 30% of records to the encoder-assisted LLM, yielding observed gains of 1.02 points on SentiCoref (interval includes zero) and 1.71 on NewsMTSC, at substantially different inference costs.

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/2611.02989 — 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 2026-11-03T18:10:07.986Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).