Using synthetic inductive reasoning tasks with a single 'aha' example, the paper shows simple gradient-norm attribution often beats integrated gradients for identifying the crucial example, while interpretability worsens in larger models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Input Attributions Explain Inductive Reasoning in In-Context Learning?
Using synthetic inductive reasoning tasks with a single 'aha' example, the paper shows simple gradient-norm attribution often beats integrated gradients for identifying the crucial example, while interpretability worsens in larger models.