#natural language process...
Jun 2026
PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents
This work introduces PARSE (Provenance-Aware Retrieval Sanitization), a domain-aware, fact-preserving sanitization pipeline that classifies each sentence by injection likelihood, extracts structured facts before rewriting, and verifies fact preservation via a consistency-checking loop.
Aaditya Pai
· arXiv.org · 0 citations