Abstract
LEED v4.1 BD+C certification remains a document-intensive process requiring reviewers to read hundreds of pages of project evidence and apply credit-specific threshold logic manually. This paper investigates whether small, locally deployed language models can effectively screen LEED documentation and how deterministic symbolic components should share that work. We introduce a neuro-symbolic pipeline that aligns project PDFs to LEED credit sections, retrieves evidence with credit-aware keyword signatures, verifies compliance with a locally hosted 4-billion-parameter language model, and applies a LEED-specific numeric checker for quantitative thresholds.
Experiments on four university buildings (484 PDFs, 153 credit-level decisions) show that the 4-billion-parameter model (gemma3:4b) is the strongest text-only core verifier, achieving 67.3% accuracy and outperforming a larger 8-billion-parameter model (llama3.1:8b) in this task. The deterministic numeric checker corrects arithmetic errors on key quantitative credits, moving EA-p2 from 50% to 100% accuracy and improving several other credits when required values are reliably extracted. Simultaneously, the full neuro-symbolic configuration achieves 61.6% overall accuracy, trailing the best text-only baseline due to extraction failures and conservative behavior on qualitative categories. Systematic ablations show that adding low-resolution drawing images (150-300 dpi) consistently reduces accuracy, and that prompt effectiveness depends on the building's ground-truth PASS rate: rubric prompts perform best on documentation-rich projects, while chain-of-thought prompts perform best on documentation-lean projects. Within the specific scope of LEED v4.1 BD+C compliance verification over raw project documentation, this pipeline and its baselines provide an initial reproducible reference point for both accuracy and failure modes.
Blogger's Review: This study showcases the potential of neuro-symbolic AI in handling complex document processing, particularly in compliance audits like LEED. By combining language models with deterministic checkers, it enhances the accuracy of compliance verification and offers important references for future document-driven AI applications. The method's sensitivity to low-quality images highlights a limitation, suggesting future improvements could focus on image processing techniques to further boost overall performance.