Hallucinations are mapped as outputs of self-attention entity confusion, MLE lack of factual constraint, and autoregressive error cascade, using an existing taxonomy.
A mathematical framework for transformer circuits,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data
Hallucinations are mapped as outputs of self-attention entity confusion, MLE lack of factual constraint, and autoregressive error cascade, using an existing taxonomy.