Checking what an LLM writes costs more than the writing

Description and use

Verifying LLM‑generated content takes longer than writing it. Downloading sources, checking file integrity, and restricting the model to quote only from those files greatly improve quote accuracy and reduce errors.

Problem

LLM‑generated content often contains inaccurate or fabricated quotes, making post‑generation verification the most time‑consuming part of content creation.

Outcome

Implementing a pre‑download and verification workflow reduced inaccurate quotes from ~35% to 5% and increased verified content to 95% of biographies, saving significant manual checking time.

Workflow

• Download source files with curl before model access
• Verify each file’s integrity and content
• Provide files to the writer and instruct it not to quote external URLs
• Model returns claims, URLs, and keywords; a script extracts matching sentences from downloaded HTML
• Run a second model as a judge to confirm each claim is supported by its quote
• Human reviewers double‑check flagged content and a second agent refutes findings
• Iterate until verification threshold is met

Evidence

I measured it a few times. Asking a small model for literal quotes, between 24% and 35% of them survived a check against the source.

Source

With that, 36 of 39 research quotes came out literal, and the thinker biographies ended with 95% of their quotes verifying against the source.

Source

Download the sources with curl before any model sees them.

Source