Metraipolis › archive › dc_de45a4e952b5

Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models — arXiv:2610.03482

Source
arXiv
Original
https://arxiv.org/abs/2610.03482
License (as archived)
CC0-1.0
Archived
2026-10-05T22:51:48.001Z
SHA-256 of the archived text
f22b5066eacbaa96bee949cabead311059ce6cd1f830f1a690d86619246ab190
Stable URL of this page
https://metraipolis.com/documento/dc_de45a4e952b5

How to cite

Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models — arXiv:2610.03482 — arXiv, https://arxiv.org/abs/2610.03482 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de45a4e952b5 (Metraipolis archive dc_de45a4e952b5, sha256 f22b5066eacbaa96bee949cabead311059ce6cd1f830f1a690d86619246ab190)
BibTeX
@misc{dcde45a4e952b5,
  title = {Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models — arXiv:2610.03482},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03482},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de45a4e952b5; sha256 f22b5066eacbaa96bee949cabead311059ce6cd1f830f1a690d86619246ab190},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03482. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hallucination detection is particularly important for medical language models, but repeated-sampling approaches are expensive and existing uncertainty-head resources do not directly transfer to a new backbone and language. We adapt the LLM Uncertainty Head (LUH) framework to Aya-Expanse-8B-based Persian medical models, using Gaokerena-V and Gaokerena-R as two previously developed backbones. We first examine response variability on a 168-question Iranian medical entrance examination and observe substantially lower five-run consistency for Gaokerena-V than for Aya-Expanse-8B, whereas Gaokerena-R is comparable to Aya-Expanse-8B. We then construct two paired claim-level hallucination datasets directly in Persian, containing 1,600 responses for each backbone, and train lightweight claim-level heads on frozen backbone attention maps and token probabilities. On held-out test splits, the heads obtain PR-AUCs of 0.4820 and 0.4652, corresponding to 2.30 and 2.66 times their respective random baselines, and ROC-AUCs of 0.7852 and 0.7810. The heads require neither retrieval nor repeated sampling at inference time. These results provide an initial study of single-pass claim-level uncertainty estimation for Persian medical language models; the test splits are small and the labels are automatically generated.

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/2610.03482 — 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 2026-10-05T22:46:10.586Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).