Pith. sign in

Title resolution pending

· 2025 · arXiv 1201.37254

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

1 Pith paper citing it
read on arXiv browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.AI 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs

cs.AI · 2026-08-13 · conditional · novelty 6.0

SEAG uses a locally fine-tuned 3-4B model to replace sensitive entities with consistent aliases in RAG prompts, letting external LLMs answer while keeping original values hidden; reported User accuracy is over 80% but full-entity hiding accuracy is only 75-78%.

citing papers explorer

Showing 1 of 1 citing paper.

  • Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs cs.AI · 2026-08-13 · conditional · none · ref 5

    SEAG uses a locally fine-tuned 3-4B model to replace sensitive entities with consistent aliases in RAG prompts, letting external LLMs answer while keeping original values hidden; reported User accuracy is over 80% but full-entity hiding accuracy is only 75-78%.