6 articles tagged with #llm-governance. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce ICCU, an in-context continual unlearning framework that removes specific data influence from language models without modifying parameters. The method uses pattern-induced refusal rules applied at inference time, addressing the inefficiency of sequential unlearning requests in production deployments.
Researchers from arXiv demonstrate that multi-agent AI systems built on large language models achieve dramatically different performance levels based on their organizational structure, with governance topology showing a 57+ percentage point performance gap. The study translates seven historical political institutions into executable multi-agent architectures, revealing that optimal organizational design shifts systematically with model capability and task requirements.
Researchers introduce the Dynamic Behavioral Constraint (DBC) benchmark, a new governance framework for large language models that reduces AI risk exposure by 36.8% through structured behavioral controls applied at inference time. The system achieves high EU AI Act compliance scores and represents a model-agnostic approach to AI safety that can be audited and mapped to different jurisdictions.
Researchers propose an AI-augmented hub-and-spoke lakehouse architecture as a practical alternative to pure data mesh implementations, combining centralized governance automation with domain team autonomy. The model uses large language models to standardize data products, enforce quality rules, and democratize data access while enabling incremental responsibility transfer from central teams to domain teams as they mature.
Researchers propose a deployment-side governance framework for managing Large Language Model updates, addressing the problem of silent behavioral changes in hosted LLM services that lack explicit versioning. The framework combines production contracts, risk-category-based testing, and compatibility gates to prevent regressions in functionality, safety, and performance.
A grounded theory study of 33 designers and developers reveals that organizational acceptance of LLMs depends on how they're positioned within workflows: as controlled tools versus collaborative teammates. Clear human authority and accountability enable integration, while ambiguous agency creates resistance, suggesting LLM adoption is fundamentally a sociotechnical positioning problem rather than a technical capability question.
