A frozen LLM answers graph reasoning questions when a learned knowledge-graph embedding vector is prepended to the query, outperforming prompting baselines in the reported experiments.
The gauge coupling unification in Grand Unified Theories based on the group $E_8$
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider a theory with the gauge group $E_8$ assuming that the gauge symmetry breaking pattern is $E_8 \to E_7 \times U_1 \to E_6 \times U_1 \to SO_{10} \times U_1 \to SU_5 \times U_1 \to SU_3 \times SU_2 \times U_1$ and vacuum expectation values are acquired only by components of the representations 248. It is demonstrated that in this case there are several options for the relations between the gauge couplings of the resulting theory, but only one of them gives $\alpha_3 = \alpha_2$ and $\sin^2\theta_W = 3/8$. Also, it is the only option for which the resulting theory can include all MSSM superfields.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Injecting Knowledge Graphs into Large Language Models
A frozen LLM answers graph reasoning questions when a learned knowledge-graph embedding vector is prepended to the query, outperforming prompting baselines in the reported experiments.