Picture for Qinghua Lu

Qinghua Lu

Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents

Add code
May 16, 2024
Viaarxiv icon

Resolving Ethics Trade-offs in Implementing Responsible AI

Jan 16, 2024
Figure 1 for Resolving Ethics Trade-offs in Implementing Responsible AI
Figure 2 for Resolving Ethics Trade-offs in Implementing Responsible AI
Figure 3 for Resolving Ethics Trade-offs in Implementing Responsible AI
Figure 4 for Resolving Ethics Trade-offs in Implementing Responsible AI
Viaarxiv icon

Navigating Privacy and Copyright Challenges Across the Data Lifecycle of Generative AI

Nov 30, 2023
Viaarxiv icon

Building the Future of Responsible AI: A Reference Architecture for Designing Large Language Model based Agents

Add code
Nov 28, 2023
Viaarxiv icon

Towards Self-Interpretable Graph-Level Anomaly Detection

Add code
Oct 25, 2023
Figure 1 for Towards Self-Interpretable Graph-Level Anomaly Detection
Figure 2 for Towards Self-Interpretable Graph-Level Anomaly Detection
Figure 3 for Towards Self-Interpretable Graph-Level Anomaly Detection
Figure 4 for Towards Self-Interpretable Graph-Level Anomaly Detection
Viaarxiv icon

Decentralised Governance for Foundation Model based AI Systems: Exploring the Role of Blockchain in Responsible AI

Aug 31, 2023
Viaarxiv icon

Test-takers have a say: understanding the implications of the use of AI in language tests

Jul 19, 2023
Figure 1 for Test-takers have a say: understanding the implications of the use of AI in language tests
Figure 2 for Test-takers have a say: understanding the implications of the use of AI in language tests
Figure 3 for Test-takers have a say: understanding the implications of the use of AI in language tests
Figure 4 for Test-takers have a say: understanding the implications of the use of AI in language tests
Viaarxiv icon

Enhancing Virtual Assistant Intelligence: Precise Area Targeting for Instance-level User Intents beyond Metadata

Jun 07, 2023
Figure 1 for Enhancing Virtual Assistant Intelligence: Precise Area Targeting for Instance-level User Intents beyond Metadata
Figure 2 for Enhancing Virtual Assistant Intelligence: Precise Area Targeting for Instance-level User Intents beyond Metadata
Figure 3 for Enhancing Virtual Assistant Intelligence: Precise Area Targeting for Instance-level User Intents beyond Metadata
Figure 4 for Enhancing Virtual Assistant Intelligence: Precise Area Targeting for Instance-level User Intents beyond Metadata
Viaarxiv icon

A Framework for Designing Foundation Model based Systems

Add code
May 21, 2023
Figure 1 for A Framework for Designing Foundation Model based Systems
Figure 2 for A Framework for Designing Foundation Model based Systems
Figure 3 for A Framework for Designing Foundation Model based Systems
Figure 4 for A Framework for Designing Foundation Model based Systems
Viaarxiv icon

Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects

Apr 21, 2023
Viaarxiv icon