Design Behaviour Codes (DBCs): A Taxonomy-Driven Layered Governance Benchmark for Large Language Models

--> Computer Science > Artificial Intelligence arXiv:2603.04837 [Submitted on 5 Mar 2026] Title: Design Behaviour Codes : A Taxonomy-Driven Layered Governance Benchmark for Large Language Models Authors: G. Madan Mohan , Veena Kiran Nambiar , Kiranmayee Janardhan View a PDF of the paper titled Design Behaviour Codes : A Taxonomy-Driven Layered Governance Benchmark for Large Language Models, by G. Madan Mohan and 2 other authors View PDF Abstract: We introduce the Dynamic Behavioral Constraint benchmark, the first empirical framework for evaluating the efficacy of a structured, 150-control behavioral governance layer, the MDBC (Madan DBC) system, applied at inference time to large language models . Unlike training time alignment methods (RLHF, DPO) or post-hoc content moderation APIs, DBCs constitute a system prompt level governance layer that is model-agnostic, jurisdiction-mappable, and auditable. We evaluate the DBC Framework across a 30 domain risk taxonomy organized into six clusters (Hallucination and Calibration, Bias and Fairness, Malicious Use, Privacy and Data Protection, Robustness and Reliability, and Misalignment Agency) using an agentic red-team protocol with five adversarial attack strategies (Direct, Roleplay, Few-Shot, Hypothetical, Authority Spoof) across 3 model families. Our three-arm controlled design (Base, Base plus Moderation, Base plus DBC) enables causal attribution of risk reduction. Key findings: the DBC layer reduces the aggregate Risk Exposure Rate from 7.19 percent to 4.55 percent (Base plus DBC), representing a 36.8 percent relative risk reduction, compared with 0.6 percent for a standard safety moderation prompt. MDBC Adherence Scores improve from 8.6 by 10 to 8.7 by 10 (Base plus DBC). EU AI Act compliance (automated scoring) reaches 8.5by 10 under the DBC layer. A three judge evaluation ensemble yields Fleiss kappa greater than 0.70 (substantial agreement), validating our automated pipeline. Cluster ablation identifies the Integrity...