Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG
A structured four-stage prompt framework translates raw traffic rules into executable Prolog, reaching 75% accuracy versus 60% and 55% for baselines.
The S4L→Prolog framework performs semantic role extraction, scene completion, logical mapping, and Prolog rule generation within a single guided prompt, converting natural-language legal rules into executable logic without human intervention. On a benchmark of twenty real-world traffic rules it correctly formalized 75% of rules, beating NL→Prolog (60%) and LE→Prolog (55%). Qualitative analysis found it better captures implicit causal relations, deontic modality, and exception structure.
- S4L framework combines four reasoning stages in one guided prompt
- 75% accuracy on twenty real-world traffic rules versus 60% and 55% baselines
- Better captures causal relations, deontic modality, and exception structure
- Targets safety-critical legal rule formalization for computational reasoning engines
From the original article
1 min read at arxiv.orgTraffic regulations are written for human interpretation and therefore rely on shared background knowledge and flexible phrasing, which inherently introduce ambiguity, context dependence, and semantic underspecification. These linguistic characteristics conflict with the precision required by computational reasoning engines such as Prolog, which demand explicit logical structure.
By May Myo Zin · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.