Pith. sign in

alespalla/chatbot_instruction_prompts dataset

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

1 Pith paper citing it

fields

cs.CR 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Sentinel: SOTA model to protect against prompt injections

cs.CR · 2025-06-05 · conditional · novelty 4.0

Sentinel, a ModernBERT-based binary classifier trained on public and private prompt datasets, reports 0.987 accuracy and 0.980 F1 on a held-out internal test set and outperforms one baseline on public benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Sentinel: SOTA model to protect against prompt injections cs.CR · 2025-06-05 · conditional · none · ref 2

    Sentinel, a ModernBERT-based binary classifier trained on public and private prompt datasets, reports 0.987 accuracy and 0.980 F1 on a held-out internal test set and outperforms one baseline on public benchmarks.