Amortized optimization with policy gradients and graph knowledge selects informative word subsets to explain black-box DLM outputs.
Bowman, Jon Gauthier, Abhinav Rastogi, Raghav Gupta, Christo- pher D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets
Amortized optimization with policy gradients and graph knowledge selects informative word subsets to explain black-box DLM outputs.