Skip to content
conftrace_
2026 AACL AACL 2026

The Geometry of Uncertainty in Language Model Representations

AbstractHidden-state probes have been used to predict factual errors in language-model outputs. We study whether the same representations also distinguish four types of prompt-model relationship: known, unknown, ambiguous, and misleading (built on a false premise). On a controlled 200-prompt dataset constructed to balance six surface features, all six pairwise type contrasts are linearly recoverable from hidden states at the position where generation begins, at AUROC ≥ 0.986 on three open-weight instruction-tuned models spanning two families and a fourfold parameter range. The probe exceeds surface-feature, TF-IDF, and frozen sentence-embedding baselines on every pair. Under group-aware evaluation on paraphrased prompts with group-level shuffled controls, probe AUROC remains at least 0.949 on every pair while lexical baselines degrade. These findings frame hallucination as one downstream consequence of a four-type representational structure that also captures ambiguity and false premises.

More from AACL 2026

All AACL 2026 papers →