A sentence-level prototype surrogate is trained to imitate LLM predictions and its prototype matches are used as explanations; the paper claims state-of-the-art faithfulness with moderate evidence.
Distill-and-compare: Auditing black-box models using transparent model distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning to Explain: Prototype-Based Surrogate Models for LLM Classification
A sentence-level prototype surrogate is trained to imitate LLM predictions and its prototype matches are used as explanations; the paper claims state-of-the-art faithfulness with moderate evidence.