Public articles linked to the same research event.
arXiv The work proposes Law&Order, a neuro-symbolic framework that combines large language model synthesis with cell-level verification and iterative localized error repair using human-written OpenTaxSolver tax returns to automatically formalize tax forms and instructions into executable symbolic programs, establishing structural correspondence aligning legal and symbolic components such as cells and schedules and denotational correspondence requiring symbolic components to implement the computations specified by their legal counterparts; evaluated on independently authored, held-out TaxCalcBench returns never exposed during generation or repair, the most advanced LLM achieves only 66% accuracy while Law&Order achieves 100% cell-level and form-level accuracy on 51 held-out returns.
The work proposes Law&Order, a neuro-symbolic framework that combines large language model synthesis with cell-level verification and iterative localized error repair using human-written OpenTaxSolver tax returns to automatically formalize tax forms and instructions into executable symbolic programs, establishing structural correspondence aligning legal and symbolic components such as cells and schedules and denotational correspondence requiring symbolic components to implement the computations specified by their legal counterparts; evaluated on independently authored, held-out TaxCalcBench returns never exposed during generation or repair, the most advanced LLM achieves only 66% accuracy while Law&Order achieves 100% cell-level and form-level accuracy on 51 held-out returns.
The work proposes Law&Order, a neuro-symbolic framework that combines large language model synthesis with cell-level verification and iterative localized error repair using human-written OpenTaxSolver tax returns to automatically formalize tax forms and instructions into executable symbolic programs, establishing structural correspondence aligning legal and symbolic components such as cells and schedules and denotational correspondence requiring symbolic components to implement the computations specified by their legal counterparts; evaluated on independently authored, held-out TaxCalcBench returns never exposed during generation or repair, the most advanced LLM achieves only 66% accuracy while Law&Order achieves 100% cell-level and form-level accuracy on 51 held-out returns.
The work proposes Law&Order, a neuro-symbolic framework that combines large language model synthesis with cell-level verification and iterative localized error repair using human-written OpenTaxSolver tax returns to automatically formalize tax forms and instructions into executable symbolic programs, establishing structural correspondence aligning legal and symbolic components such as cells and schedules and denotational correspondence requiring symbolic components to implement the computations specified by their legal counterparts; evaluated on independently authored, held-out TaxCalcBench returns never exposed during generation or repair, the most advanced LLM achieves only 66% accuracy while Law&Order achieves 100% cell-level and form-level accuracy on 51 held-out returns.