A new evaluation framework claims to quantify LLM distillation using identity-jailbreak contradictions and response similarity, ranking most major LLMs as highly distilled except Claude, Doubao, and Gemini.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Quantification of Large Language Model Distillation
A new evaluation framework claims to quantify LLM distillation using identity-jailbreak contradictions and response similarity, ranking most major LLMs as highly distilled except Claude, Doubao, and Gemini.