Metraipolis › archive › dc_a552c64bc6f2
When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev — arXiv:2609.39496
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39496
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:14:25.630Z
- SHA-256 of the archived text
32f1600ff3d519183d50edb577d07522f8ded6e05a2bbf951e2de0a6798d3ec1- Stable URL of this page
https://metraipolis.com/documento/dc_a552c64bc6f2
How to cite
When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev — arXiv:2609.39496 — arXiv (en), https://arxiv.org/abs/2609.39496 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a552c64bc6f2 (Metraipolis archive dc_a552c64bc6f2, sha256 32f1600ff3d519183d50edb577d07522f8ded6e05a2bbf951e2de0a6798d3ec1)
BibTeX
@misc{dca552c64bc6f2,
title = {When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev — arXiv:2609.39496},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39496},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a552c64bc6f2; sha256 32f1600ff3d519183d50edb577d07522f8ded6e05a2bbf951e2de0a6798d3ec1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39496. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Typed decision models such as Jev offer an efficient alternative to generative LLMs in decision-making workflows by selecting directly from predefined options. When candidate sets contain no valid answer, TypeSafe recommends including an "other" or "none-of-the-above" option to enable rejection. In this report, however, we identify an arithmetic-dependent rejection bottleneck: Jev reliably selects correct numerical answers when available but frequently accepts incorrect alternatives when they are absent despite an explicit rejection option. On paired arithmetic problems, answer-present accuracy reaches 99%, while correct rejection falls to 7%. Moreover, this gap persists across numerical magnitudes, operation depths, contextual formulations, and rejection labels, and extends to scenarios such as time calculation and capacity rounding. Yet native Boolean verification achieves 99% exact-match accuracy on the same answer-absent arithmetic cases, showing that categorical rejection can fail even when the model successfully verifies candidate correctness. Finally, we show that a simple decision threshold selected on separate development problems raises arithmetic rejection accuracy from 7% to 79% while retaining 97% answer-present accuracy, substantially mitigating the failure without retraining or additional inference. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.39496 — 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 2026-10-07T12:44:51.965Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).