Metraipolis › archive › dc_0f650c0ff70f

Calibrating Small Language Models for Claim Check-Worthiness Detection — arXiv:2608.30731

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30731
License (as archived)
CC0-1.0
Archived
2026-10-17T07:52:58.058Z
SHA-256 of the archived text
12b4326a68e069269cd8ad8a7bd36b80fb0cc3255cf44ba1f557f0ae18a1fd98
Stable URL of this page
https://metraipolis.com/documento/dc_0f650c0ff70f

How to cite

Calibrating Small Language Models for Claim Check-Worthiness Detection — arXiv:2608.30731 — arXiv (en), https://arxiv.org/abs/2608.30731 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f650c0ff70f (Metraipolis archive dc_0f650c0ff70f, sha256 12b4326a68e069269cd8ad8a7bd36b80fb0cc3255cf44ba1f557f0ae18a1fd98)
BibTeX
@misc{dc0f650c0ff70f,
  title = {Calibrating Small Language Models for Claim Check-Worthiness Detection — arXiv:2608.30731},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30731},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f650c0ff70f; sha256 12b4326a68e069269cd8ad8a7bd36b80fb0cc3255cf44ba1f557f0ae18a1fd98},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30731. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challenge at an early-stage startup: running large language models (LLMs) over every incoming claim is cost- and latency-prohibitive, yet smaller models sacrifice accuracy. We propose NN-PPI, a pointwise extension of Prediction-Powered Inference (PPI) that calibrates model predictions at inference time as a lightweight post-hoc layer, without re-training the underlying model. NN-PPI achieves weighted F1 gains ranging from 12% to 33.80% depending on the size and performance of the baseline model, bringing SLMs on par with larger LLMs. Beyond few-shot SLMs, NN-PPI further improves a production-deployed fine-tuned model, demonstrating that residual calibration is complementary to supervised fine-tuning. By recovering LLM-level accuracy from models that are an order of magnitude cheaper to serve, it makes accurate check-worthiness detection substantially cheaper to operate at scale. Our code and data can be found at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30731 — 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 2026-10-17T07:28:26.905Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).