LLMs recover dominant binomial orders from corpora but align less closely with exact preference distributions, with preference strength partially encoded in middle-to-late layers and manipulable via steering.
Graph Convolutional Networks for Text Classification , url =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Graph neural networks on assurance case graphs reach 0.76 ROC-AUC for link prediction and 0.94 F1 for distinguishing human from LLM-generated cases, with observed differences in hierarchical linking patterns.
citing papers explorer
-
Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models
LLMs recover dominant binomial orders from corpora but align less closely with exact preference distributions, with preference strength partially encoded in middle-to-late layers and manipulable via steering.
-
Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis
Graph neural networks on assurance case graphs reach 0.76 ROC-AUC for link prediction and 0.94 F1 for distinguishing human from LLM-generated cases, with observed differences in hierarchical linking patterns.