Hidden State Geometry Predicts Hallucination Before Generation: A Universal Pre-Generation Detector Across 7 Architectures

This record contains the full replication package for the paper"Hidden State Geometry Predicts Hallucination Before Generation: A Universal Pre-Generation Detector Across 7 Architectures" (Blaschuk, 2026). We demonstrate that the geometry of hidden states encodes a reliablesignal of hallucination before a single output token is generated. Using linear probes on residual stream activations from 7 languagemodel architectures (GPT-2-XL, Llama-3. 1, Gemma-2, Mistral-7B, OPT, Phi-3, Falcon), we show that a pre-generation linear classifier predictshallucination with ROC-AUC 0. 652-0. 757 (mean 0. 695) across all 7 models, significantly above chance (0. 500). Live validation on Llama 3. 1-8B-Instructconfirms AUC = 0. 740. Layer sweep across all 32 layers reveals monotonicaccumulation of hallucination signal from layer 0 (AUC = 0. 628) tolayer 26 (AUC = 0. 757). Contents: BlaschukPreGenerationHallucination₂026. pdf — full paper replicationₛcript. py — end-to-end replication pipeline (Python) pregenₕiddensₗlama31. pkl — pre-generation hidden states, Llama 3. 1-8B-Instruct, N=283 hallucinationdetectorFINAL. pkl — numerical results fig1ₚcaₑfₛeparation. png through fig7confusionₘatrix. png — all figures This work is part of the DSAOP research series and builds directly on: Blaschuk (2026), DOI: 10. 5281/zenodo. 19455867 Alieksieienko (2026), DOI: 10. 5281/zenodo. 19415238