Hand-checking LLM output: a guided, citation-backed workspace
Boyce Data Science · Free Tools

Hand-checking the output of a language model

A guided workspace for verifying what an LLM gives you: decompose it, check every claim and citation against a source, and leave with an evaluation record you can defend. Each step is backed by the published method it comes from.

The order is the method. Reading an LLM's output for plausibility in a single pass is exactly what lets fabricated quotes, invented citations, and confident wrong numbers through. Work the thread top to bottom; tie a knot wherever you find something.

Stage 00 · Provenance

Record what produced this output

Before judging anything, capture the conditions. Non-deterministic output can't be reproduced from a prompt alone, so the record is the artifact, and disclosure of model, version, and use is what reporting guidelines now require.

Reporting guideline
Gallifant et al. (2025). The TRIPOD-LLM reporting guideline. Nat Med 31:60–69 · interactive checklist
Emphasizes transparency, human oversight, and task-specific performance reporting.
Disclosure
Cacciamani et al. (2023). CANGARU Guidelines. arXiv:2307.08974
Cross-disciplinary standard for disclosing and reporting generative-AI use in scholarship.

Provenance fields

Evaluation record

Your compiled result

This updates as you work. Export it as JSON to archive or re-open later, or print it to PDF as a standalone evaluation record.

Provenance

Claims examined

Findings by stage

References

Every method in this tool traces to one of these. Links were checked to resolve; nothing here is generated. If a link ever breaks, the DOI or arXiv ID will still find it.

Built as a free tool by Boyce Data Science. Use it, adapt it, cite the underlying papers.  ·  Verify & cite. Don't trust the plausibility of the prose.