cs.CLNov 13, 2026

UltraBERT-JEV: Encoder models for System One Applications

Authors: Astarag Mohapatra

Organizations: Independent Researcher

Abstract

We study encoder models that pick one of several options in a single forward pass, without generating text. This technical report compares recipes for fine-tuning UltraBERT-380M with one mask per option. The four recipes differ in how an option is scored and how the scores become probabilities; one follows the expert gate of DeepSeek-V3. Trained on the same data as Qwen3-0.6B with the LLM-as-Jev recipe (67.6% test accuracy), the encoder reaches 69.7% to 72.1%. Scoring an option by "yes" minus "no" instead of "yes" alone gives the larger gain, from 69.7% to 71.3% on the test set and from 57.8% to 59.6% on external benchmarks (56.1% for the decoder). Sigmoid normalisation adds 0.8 test points; a square-root softplus adds none. One request at a time on an NVIDIA A100, the encoder takes 29 ms per decision against 68 ms, but uses more peak memory (2.8 against 2.2 GiB). An auxiliary head, trained on human-marked evidence and on labels selected with a reward adapted from SelfCite, predicts in the same pass the sentences annotated as support for the answer.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. UltraBERT: Beyond the Limit of BERT Pre-Training

    Oct 10, 2026Jungwoo Park, Taewhoo Lee, Jaewoo KangLanguage Model PretrainingMasked Language Modeling