Skip to content

How legal AI is used

Prompt Engineering Impact

How prompting technique changes accuracy, completeness and relevance of legal answers.

IllustrativoAggiornato 2026-07-08

Across eight prompting techniques in this illustrative scenario, accuracy ranges from 62 on zero-shot queries to a high of 91 for multi-step decomposition, with jurisdiction-scoped prompts scoring highest on relevance (92) and structured-output prompting leading on completeness (90). Chain-of-thought and role-based framing land in the middle of the pack. The spread suggests query structure, not just model choice, is a meaningful lever for output quality. That points legal teams toward prompt design and jurisdiction-scoping as a lower-cost improvement path than model switching. These figures are illustrative, not measured benchmarks.

I dati

Prompt Engineering Impact - How prompting technique changes accuracy, completeness and relevance of legal answers.
Prompting techniqueAccuracyCompletenessRelevance
Zero-shot (basic query)62%55%68%
Few-shot (with examples)78%72%82%
Chain-of-thought84%80%86%
Role-based (act as lawyer)81%78%88%
Structured output (JSON/tables)88%90%84%
Multi-step decomposition91%88%90%
Jurisdiction-scoped86%82%92%
Citation-required82%76%80%

Stima illustrativa - una cifra orientativa per l'inquadramento dello scenario, non un benchmark misurato. Non interpretare questi dati come risultati misurati per fornitore.

Torna al report Legal AI Index

Ricerche correlate

Torna ai Labs