Deep and shallow biases in language models
Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, but it does not distinguish stable model preferences from responses that depend on a particular prompt wording. We introduce a bias depth score that measures both how strongly a model prefers its top answer under direct prompting and whether that answer survives scenario reframing. Across 4,442 opinion prompts and four large language models, only about a quarter of the concentrated preferences survive reframing. We call these persistent cases Deep biases, and the remaining prompt-dependent cases Shallow biases. Our results show that Deep bi...
| Authors | An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen et al. |
|---|---|
| Primary category | cs.CL |
| Published | 9 September 2026 |
| Last updated at source | 9 September 2026 |
Connected in the knowledge graph
- anvo25/deep-biasDataset · cited by
Models and datasets referencing this paper
- anvo25/deep-biasDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.