Introduces Lexical Alignment Score and Triangulated Preference Shift metrics to automatically identify lexical overuse in LLMs and attribute portions to preference learning stages via windowed prevalence on PubMed data.
Title resolution pending
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
-
Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models
Introduces Lexical Alignment Score and Triangulated Preference Shift metrics to automatically identify lexical overuse in LLMs and attribute portions to preference learning stages via windowed prevalence on PubMed data.