Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CE 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Beyond the Black Box: Interpretability of LLMs in Finance

cs.CE · 2025-05-14 · conditional · novelty 4.0

The paper demonstrates, through illustrative experiments, that logit lens, attribution patching, sparse autoencoder features, and feature steering can be applied to financial LLM tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Beyond the Black Box: Interpretability of LLMs in Finance cs.CE · 2025-05-14 · conditional · none · ref 13

    The paper demonstrates, through illustrative experiments, that logit lens, attribution patching, sparse autoencoder features, and feature steering can be applied to financial LLM tasks.