Evolutionary trees from LLM weights recover ground-truth training topologies and identify key datasets and layers through phenotypic analysis.
Phylolm: Inferring the phylogeny of large language models and predicting their performances in benchmarks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
ABLE constructs model embeddings from gradient-based input attributions, enabling training-free LLM comparison across 239 models with theoretical stability guarantees.
citing papers explorer
-
Analysis and Explainability of LLMs Via Evolutionary Methods
Evolutionary trees from LLM weights recover ground-truth training topologies and identify key datasets and layers through phenotypic analysis.
-
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
ABLE constructs model embeddings from gradient-based input attributions, enabling training-free LLM comparison across 239 models with theoretical stability guarantees.