2 papers
cs.CL2025
`Generalization is hallucination' through the lens of tensor completions
Liang Ze Wong
In this short position paper, we introduce tensor completions and artifacts and make the case that they are a useful theoretical framework for understanding certain types of halluc…
cs.LG2025
Paying Attention to Facts: Quantifying the Knowledge Capacity of Attention Layers
Liang Ze Wong
In this paper, we investigate the ability of single-layer attention-only transformers (i.e. attention layers) to memorize facts contained in databases from a linear-algebraic persp…