Model Releases
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
arXiv:2609.02959v1 Announce Type: cross Abstract: What does a language model predict when it has few clues? The answer lurks in its unembedding geometry: a single direction of the unembedding matrix e
arXiv:2609.02959v1 Announce Type: cross Abstract: What does a language model predict when it has few clues? The answer lurks in its unembedding geometry: a single direction of the unembedding matrix encodes the unigram distribution of the training corpus, which serves as the Bayesian prior the model falls back on when uncertain. This structure --- which we term the direction of ignorance --- appears in all four model families examined (exttt{Llama}, exttt{Qwen}, exttt{Gemma}, and exttt{Pythia}), ranging from 0.4B to 405B parameters. Projecting the final prediction state onto this direction yields a per-token prior loading factor lambda, which, empirically, declines steadily as the context becomes more informative. Formally, the same projection decomposes the prediction state into two orthogonal vectors that correspond exactly to the two factors of a tempered Bayesian update: a unigram prior raised to the exponent lambda and a context-driven likelihood. This geometric-probabilistic interpretation calibrates lambda, making it meaningfully comparable across model sizes and families, with larger models generally exhibiting lower prior reliance in the high-context limit. Finally, we show that the direction of ignorance is causally active: raising or lowering lambda at the final prediction state steers the prediction toward or away from the unigram prior in KL divergence.
Related
- NanoKnow: How to Know What Your Language Model Knows
- Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory
- Learning When to Trust via Selective Context Preference Optimization
- Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
Source: arXiv cs.AI | 2026-09-04