Skip to content

Author

Jiajun Bao

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Causal and Interpretable Structures in LLM Compositional Tasks

This work studies activations from ensembles of prompts that require inferring relationships between three tokens corresponding to a cyclic concept to correctly predict the next token and finds a consistent layerwise progression in how the joint dependence among the tokens is geometrically organized and causally used.

Gurbir Arora, To-Ni J. B. Liu, Jiajun Bao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors

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, with larger models generally exhibiting lower prior reliance in the high-context limit.

To-Ni J. B. Liu, Jiajun Bao, Yizhou Liu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.