PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents

Abstract

Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and interleave legitimate authority language with factual content. We demonstrate this gap with a real-document benchmark of 122 tasks across five professional domains (financial, legal, medical, scientific, DevOps) using actual SEC filings, Federal Register rules, PubMed abstracts, arXiv papers, and GitHub postmortems. Paraphrasing, the strongest defense on synth

Categories

Framework mappings

Suggested from the entry's categories.

@misc{pai2026parse,
  title = {{PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents}},
  author = {Aaditya Pai},
  year = {2026},
  month = jun,
  eprint = {2606.17467},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.17467}
}