# Jev Matches 7B Language Models for Speech-Neuroprosthesis Rescoring

arXiv: https://arxiv.org/abs/2609.33538 · HTML: https://mlsanity.com/paper/2609.33538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [RescoreBERT: Discriminative Speech Recognition Rescoring with BERT](https://mlsanity.com/paper/2202.01094/) (2022)
- [Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models](https://mlsanity.com/paper/2310.07712/) (2023)
- [Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems](https://mlsanity.com/paper/2204.00212/) (2022)
- [Evaluating Decision Models for Text Annotation in Computational Social Science](https://mlsanity.com/paper/2609.24574/) (2026)
- [Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration](https://mlsanity.com/paper/2609.22753/) (2026)
- [One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation](https://mlsanity.com/paper/2604.27599/) (2026)
- [Discriminative Speech Recognition Rescoring with Pre-trained Language Models](https://mlsanity.com/paper/2310.06248/) (2023)
- [Position Bias Undermines Preference Consistency in Listwise LLM-Based Reranking](https://mlsanity.com/paper/2608.03091/) (2026)

## Abstract (arXiv)

A speech neuroprosthesis decodes attempted speech from brain activity and ends by rescoring the decoder's candidate sentences with a language model of several billion parameters, the only component that needs a GPU. Replacing that model with a cheaper one is hard: general language models asked to pick one sentence from a list answer from where a label sits in the list rather than from the sentence itself. We pose rescoring as a single typed decision, one call that returns a probability for every candidate, served by Jev, a hosted model trained for calibrated decisions, and combine it with the decoder's own score. On 978 held-out sentences from a participant with ALS, where the published decoder alone reaches 8.1% word error, Jev reaches 7.5% against 7.8% for both OPT-6.7b and Qwen2.5-7B; with the decoder's weight re-tuned, 6.9% against 7.2% and 7.4%. Jev is ahead in all four comparisons and at most 0.2 points behind at the 95% bound. It costs 0.07 USD per thousand sentences and needs no GPU; a dedicated GPU running a 7B model is cheaper per sentence only above 43% utilisation, far beyond what one user generates. End-to-end latency over the internet is 262 ms, of which 62 ms is spent at the provider, the same order as a 7B model on a local GPU (27 ms) but not faster.