FST Graduate Research Topic


Research Topic: Intelligent Corporate Legal Compliance Monitor
Suggested By: Harris Wang
Last Update: September 28th, 2025

Constrained Object Hierarchies (COH) provides a neuroscience-inspired theoretical framework for modeling Artificial General Intelligence (AGI). As a flexible and robust foundation, COH supports the representation of general intelligent systems across diverse domains.


Formally, a COH is defined as a 9-tuple:


O = (C, A, M, N, E, I, T, G, D)


Where:



  • C: Components – sub-objects organized hierarchically

  • A: Attributes – state variables describing object properties

  • M: Methods – executable actions associated with components

  • N: Neural Components – adaptive models for learning and inference

  • E: Embedding Neural Component – semantic representation of the COH

  • I: Identity Constraints – rules ensuring object integrity

  • T: Trigger Constraints – event-condition-action rules for dynamic behavior

  • G: Goal Constraints – optimization objectives guiding intelligent behavior

  • D: Constraint Daemons – real-time monitors enforcing system constraints





Based on the COH framework, the modelling process and result of Intelligent Corporate Legal Compliance Monitor are as follows:


Description and Significance: This system uses NLP to monitor changes in regulations, internal communications, and contracts to ensure the company operates within legal boundaries. It represents the application of AI to corporate governance, transforming compliance from reactive auditing to proactive intelligence.


Analysis and Requirements: The system must parse complex legal documents, understand their business implications, and flag potential compliance issues before they escalate. Key requirements include legal document analysis, risk assessment accuracy, and integration with business processes.


Design of the COH Solution: The monitor is designed as a knowledge-based system where legal rules are encoded as identity constraints, and neural components map real-world data onto these rules for continuous compliance assessment.


COH Modelling Solution:



  • C: {RegulatoryFeedParser, ContractAnalyzer, EmployeeCommsScanner, RiskAssessor}

  • A: {ComplianceStatus, RegulatoryChangeLog, IdentifiedRiskLevel, MitigationAction}

  • M: {ParseNewRegulation(), AssessCompliance(), FlagIssue(), SuggestMitigation()}

  • N: Legal LLMs fine-tuned for compliance risk classification

  • E: "Proactively ensuring all business activities adhere to legal and regulatory frameworks"

  • I: All activities must comply with applicable laws; Attorney-client privilege maintained

  • T: ON (NewRegulationPublished) IF (AffectsOurIndustry) THEN (AlertLegalTeam)

  • G: Minimize legal and compliance risk exposure

  • D: Continuous monitors for compliance pattern deviations


COH effectively grounds abstract legal concepts into explicit, machine-checkable identity constraints. The neural components handle complex legal interpretation while the framework ensures outputs are evaluated against concrete compliance rules.





You may choose this topic and pursue one of the following routes:


📝 Essay



  • Survey existing methodologies for modeling, designing, and implementing similar intelligent systems.

  • Include:

    • Literature synthesis

    • COH framework analysis

    • Critical evaluation of competing approaches




🛠️ Project



  • Design and implement the system using the COH model.

  • Include:

    • System architecture and design

    • Development and testing

    • Demonstration of core functionality




🎓 Thesis



  • Explore COH’s theoretical foundations in depth.

  • Include:

    • Proposed enhancements or extensions

    • Implementation and evaluation

    • Development of an advanced intelligent system grounded in COH principles