AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers introduce Harness-MU, a model-agnostic infrastructure framework that enforces multi-user governance for LLM agents through runtime execution hooks rather than prompt-based safeguards. The system guarantees permission boundaries and data privacy across adversarial multi-turn interactions while improving utility scores by 0.28-0.39 and instruction-following accuracy by up to 48.9 percentage points on benchmark tests.
AIBullisharXiv – CS AI · Jun 237/10
🧠OGD4All is a Large Language Model framework that enables citizens to interact with geospatial open government data through natural language queries, achieving 98% analytical correctness and 94% recall while minimizing hallucinations. The system combines semantic retrieval, agentic reasoning, and sandboxed execution to provide transparent, auditable access to public datasets, representing a significant advance in making government data democratically accessible.
AINeutralarXiv – CS AI · May 277/10
🧠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.
AINeutralarXiv – CS AI · May 17/10
🧠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.
AIBullisharXiv – CS AI · Mar 67/10
🧠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.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce a framework for evaluating how LLM providers control user interaction styles through alignment mechanisms, measuring prompt steerability and regression-to-default behaviors across dialogue. The study reveals that provider-side controls shape not just safety but also communicative defaults that influence user autonomy, with implications for pluralism and democratic agency in human-AI systems.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers conducted interviews with 13 early adopters building multi-agent LLM systems at a major technology organization to understand how they conceptualize and practice transparency. The study identifies five key transparency frameworks—reproducibility, debugging, boundary-setting, visualization, and auditing—revealing that transparency in distributed AI architectures is understood as a situated socio-technical practice rather than a single standardized concept.
AIBullisharXiv – CS AI · May 276/10
🧠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.
AINeutralarXiv – CS AI · May 16/10
🧠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.
AINeutralarXiv – CS AI · Apr 206/10
🧠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.
