The authors build a sentence-level interpreter by first training an energy-based surrogate of a black-box LLM, then training a lightweight network that scores prompt sentences without further API queries.
Second Conference on Language Modeling , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes
The authors build a sentence-level interpreter by first training an energy-based surrogate of a black-box LLM, then training a lightweight network that scores prompt sentences without further API queries.