# Nokia open-sources AnyJev library to turn open LLMs into calibrated decision models

Digest AI · Agents & Tools · published 2026-09-23T07:09:38Z

Canonical: https://digestai.news/story/nokia-open-sources-anyjev-library-to-turn-open-llms-into-calibrated-de

## Summary

Nokia’s applied research team released AnyJev, an open‑source Python library that converts any open‑source large language model into a typed decision model without any training. The library reads the model’s next‑token distribution, applies cyclic‑shift averaging (L0) and batch prior correction to remove position and label bias, and optionally adds temperature scaling (L1) for larger label sets.

Benchmarks on Qwen3‑8B with the 20‑way BANKING77 test set show the order‑flip rate dropping from 0.230 to 0.073, and with L1 the expected calibration error (ECE) falls to 0.036 compared with 0.144 for the original Jev system. On a 100‑label task, auto‑decidable traffic at 5 % error rises from 7.7 % to 52.0 %. The library installs from PyPI, is Apache‑2.0 licensed, and supports Hugging Face and vLLM backends; a single decision with K = 20 costs about 0.25 s on an H100 GPU at batch size 32.

AnyJev aims at production scenarios where a single answer must be chosen from a fixed set, offering a fast, training‑free alternative to fine‑tuned classifiers.

## Key points

- AnyJev turns open LLMs into calibrated decision models without training, using cyclic shifts and batch prior correction.
- On Qwen3‑8B BANKING77, order‑flip rate fell from 0.230 to 0.073 and ECE dropped to 0.036 with L1.
- Library installs via pip, runs on Hugging Face or vLLM backends, and costs ~0.25 s per decision on an H100 (K=20, batch 32).

## Why it matters

Provides a ready‑to‑use, training‑free method for reliable, calibrated decisions from open LLMs, lowering deployment cost and improving production reliability.

## Sources

1. [Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model](https://marktechpost.com/2026/09/23/nokia-open-sources-anyjev-a-training-free-layer-that-turns-any-open-llm-into-a-calibrated-decision-model) (MarkTechPost, 2026-09-23)

Part of the developing story: [OpenArch Advances LLM Architecture and Benchmarking](https://digestai.news/thread/openarch-launches-pytorch-repo-for-readable-llm-architecture-implementations) (3 stories)

## Cite

Digest AI, "Nokia open-sources AnyJev library to turn open LLMs into calibrated decision models", 23 September 2026, https://digestai.news/story/nokia-open-sources-anyjev-library-to-turn-open-llms-into-calibrated-de

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/nokia-open-sources-anyjev-library-to-turn-open-llms-into-calibrated-de.json