Entropy dynamics across token positions in intermediate layers of LLMs separate jailbreak prompts from benign ones using trend-based features without extra training.
arxiv:2206.07609 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.
citing papers explorer
-
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
Entropy dynamics across token positions in intermediate layers of LLMs separate jailbreak prompts from benign ones using trend-based features without extra training.
-
Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning
A 149M-parameter distributional energy-based verifier with low-rank adapter ensemble reduces constraint violations in structured LLM reasoning and outperforms or matches much larger models on five benchmarks.
-
Random-Set Graph Neural Networks
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.