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
Full article203 words · extracted from arxiv.org · click to collapse
Traffic 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. This study evaluates two baseline translation approaches, Natural Language to Prolog ($NL\rightarrow Prolog$) and Logical English to Prolog ($LE\rightarrow Prolog$), and introduces a new reasoning-guided translation framework called Structured Four-Stage Legal Translation ($S4L\rightarrow Prolog$). The proposed S4L framework performs semantic role extraction, scene completion, logical mapping, and Prolog rule generation within a single guided prompt, enabling direct translation of raw traffic rules into executable logic without human intervention. A benchmark consisting of twenty real-world traffic rules was used to evaluate each approach in terms of syntactic validity, semantic correctness, and logical completeness. $S4L\rightarrow Prolog$ achieves the highest accuracy, correctly formalizing 75 percent of the rules, while $NL\rightarrow Prolog$ reaches 60 percent and $LE\rightarrow Prolog$ reaches 55 percent. Qualitative analysis further shows that S4L captures implicit causal relations, deontic modality, and exception structure more reliably than the baselines. These results demonstrate that structured reasoning prompts can substantially improve the reliability of natural-language-to-logic translation for legal and safety-critical applications.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.20334