Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model
Nokia open-sources AnyJev, a training-free library that converts any open LLM into a calibrated decision model for classification tasks.
Nokia's applied research team has open-sourced AnyJev, a training-free Python library that converts open LLMs into calibrated decision models. The library uses cyclic shifts and batch prior correction to eliminate position and prior bias in next-token probabilities. Benchmarks on Qwen3-8B with the BANKING77 task show the order-flip rate drops from 0.230 to 0.073, and auto-decidable traffic at 5% error rises from 7.7% to 52.0% with the L1 calibration level.
- Nokia open-sourced AnyJev, a Python library turning any open LLM into a decision model.
- It uses cyclic shifts and batch prior correction to remove position and label bias.
- On Qwen3-8B BANKING77, it reduced order-flip rate from 0.230 to 0.073.
- Auto-decidable traffic at 5% error rose from 7.7% to 52.0% with L1 calibration.
- It supports Hugging Face and vLLM backends with shared-prefix scoring.
- Vendors
- Hugging Face
- Organizations
- Nokia
From the original article
4 min read at marktechpost.com
Nokia’s applied research team has open-sourced AnyJev, a Python library that turns an open LLM into a decision model. It needs no training. It targets a common production job: picking one answer from a fixed set instead of writing a sentence.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.