The paper demonstrates, through illustrative experiments, that logit lens, attribution patching, sparse autoencoder features, and feature steering can be applied to financial LLM tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond the Black Box: Interpretability of LLMs in Finance
The paper demonstrates, through illustrative experiments, that logit lens, attribution patching, sparse autoencoder features, and feature steering can be applied to financial LLM tasks.