Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CL 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Lightweight Safety Classification Using Pruned Language Models

cs.CL · 2024-12-18 · conditional · novelty 5.0

Intermediate-layer features of small LLMs plus a penalized logistic regression classifier achieve high F1 scores on content safety and prompt injection classification with very few labeled examples, per the paper's experiments.

citing papers explorer

Showing 1 of 1 citing paper.

  • Lightweight Safety Classification Using Pruned Language Models cs.CL · 2024-12-18 · conditional · none · ref 2

    Intermediate-layer features of small LLMs plus a penalized logistic regression classifier achieve high F1 scores on content safety and prompt injection classification with very few labeled examples, per the paper's experiments.