When Calibration Depends on the Scoring Rule: Quantized Biomedical LLM Classification
Quantized large language models can run on consumer hardware, which motivates interest in on-premises processing of sensitive data. The reliability of their confidence estimates depends on implementation choices (prompt template, label wording, and scoring normalization) that are seldom treated as experimental variables. We evaluate three 7-billion-parameter Mistral variants (a base model, BioMistral, and an instruction-tuned checkpoint evaluated without its chat template) at FP16, INT8, and INT4 on five-class sentence classification in medical abstracts. We test two primary templates on n = 2,000 test sentences and two auxiliary templates on n = 200 validation sentences. Our central obse...
| Authors | Anton Rasmussen, Hong Qin |
|---|---|
| Primary category | cs.LG |
| Published | 4 August 2026 |
| Last updated at source | 20 September 2026 |
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 Information may be incomplete or out of date.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.