PLEX learns a mapping from BERT or RoBERTa token embeddings to word importance scores, reproducing LIME and SHAP style explanations without per-sentence perturbations.
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
-
PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification
PLEX learns a mapping from BERT or RoBERTa token embeddings to word importance scores, reproducing LIME and SHAP style explanations without per-sentence perturbations.