Phi (AI model): news timeline & CVEs

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.

MarkTechPostSep 23, 07:09 UTC · 4d agoAI research

A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal

PIR reads internal states to separate concealed model knowledge from genuine ignorance across eight language models.

Probe of Internal Recognition (PIR) adapts the forensic Concealed Information Test to language models, reading internal states to see which candidate answer a model recognizes. It is reference-free, requiring neither an honest reference model nor a labeled truth corpus. Across eight models from Gemma, Qwen, Llama, Mistral, and Phi, it recovers the recognized answer at 0.70 to 0.87 balanced accuracy, above a 0.28 to 0.40 unknown-item baseline and 0.25 chance. Recognition remains 0.85 to 0.93 under prompted deception, trained sandbagging, and password-locked or circuit-broken checkpoints, but drops to the unknown-item level when unlearning removes the knowledge.

arXiv cs.AI / cs.LG / cs.CLSep 18, 16:57 UTC · 8d agoAI safety & security

Phi

Timeline2 articles

Appears with

Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model

A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal