Metraipolis › archive › dc_5526501bd1cc
One Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation — arXiv:2610.20993
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20993
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:55:44.732Z
- SHA-256 of the archived text
e1f04cde2b839901d7a01a206d6b806463479cb1eb67fa9f9158de683f547128- Stable URL of this page
https://metraipolis.com/documento/dc_5526501bd1cc
How to cite
One Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation — arXiv:2610.20993 — arXiv (en), https://arxiv.org/abs/2610.20993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5526501bd1cc (Metraipolis archive dc_5526501bd1cc, sha256 e1f04cde2b839901d7a01a206d6b806463479cb1eb67fa9f9158de683f547128)
BibTeX
@misc{dc5526501bd1cc,
title = {One Bias Score, Two Factors: How Mitigations Affect Option Bias in Multiple-Choice Evaluation — arXiv:2610.20993},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20993},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5526501bd1cc; sha256 e1f04cde2b839901d7a01a206d6b806463479cb1eb67fa9f9158de683f547128},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reordering multiple-choice options can change a model's answer, an effect studied as selection bias (a preference for certain option letters) and as order sensitivity (changes in answers across option orderings). We connect these perspectives through the pooled selection-rate standard deviation (pooled SD), which measures how unevenly option letters are selected across questions and orderings. When every option of each question appears equally often at each position, the pooled SD is exactly the product of two label-free factors: the flip rate and the positional skew. The flip rate is the fraction of questions whose chosen option changes across orderings; the positional skew is the standard deviation of option-letter selection rates among those questions. Across 41 checkpoints and 12 benchmarks, the flip rate tracks accuracy and output uncertainty, while the positional skew tracks the estimated option-symbol prior. Prior correction for selection bias mainly reduces the positional skew. Aggregating each ordering with its reversal, a mitigation for order sensitivity, mainly reduces the flip rate. Both reduce the range of accuracy across correct-answer letters by similar amounts, but aggregation leaves fewer model-rank reversals. Applying prior correction before aggregation reduces both factors and further narrows this accuracy range. However, aggregation lowers the flip rate partly by settling questions on the same wrong option. We therefore recommend reporting both factors to distinguish mitigation effects, alongside accuracy to distinguish stability from correctness. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.20993 — 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 2026-10-16T08:44:47.616Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).