Dr. Xinwei Sun from Microsoft Research Asia presented research on trustworthy AI, focusing on statistical learning with theoretical guarantees. The work covers methods for sparse recovery with false-discovery rate analysis and causal inference tools for robustness and explainability. Consistency and identifiability were addressed theoretically, with applications shown in medical imaging analysis. Why it matters: The research contributes to addressing key limitations of current AI models regarding explainability, reproducibility, robustness, and fairness, which are crucial for real-world applications in sensitive fields like healthcare.
Dr. Youcheng Sun from the University of Manchester presented on ensuring the trustworthiness of AI systems using formal verification, software testing, and explainable AI. He discussed applying these techniques to challenges like copyright protection for AI models. Dr. Sun's research has been funded by organizations including Google, Ethereum Foundation, and the UK’s Defence Science and Technology Laboratory. Why it matters: As AI adoption grows in the GCC, ensuring the safety, dependability, and trustworthiness of these systems is crucial for public trust and responsible innovation.
Amir Goharshady from Hong Kong University of Science and Technology presented a talk at MBZUAI on martingale-based verification of probabilistic programs. The talk covered using martingale-based approaches for proving termination and synthesizing cost bounds for probabilistic programs, automating program analysis with template-based methods. He also discussed remaining challenges and open problems in the area. Why it matters: Advances in formal verification and analysis of probabilistic programs are crucial for ensuring the reliability and safety of AI systems that rely on randomization.
MBZUAI faculty Kun Zhang is researching methods to improve the reliability of generative AI, particularly in healthcare applications. Current generative AI models often act as "black boxes," making it difficult to understand why a specific result was produced. Zhang's research focuses on incorporating causal relationships into AI systems to ensure more accurate and meaningful information. Why it matters: Improving the trustworthiness of generative AI is crucial for sensitive sectors like healthcare and ensuring responsible AI deployment across the region.
Researchers from MBZUAI developed "uncertainty quantification heads" (UQ heads) to detect hallucinations in language models by probing internal states and estimating the credibility of generated text. UQ heads leverage attention maps and logits to identify potential hallucinations without altering the model's generation process or relying on external knowledge. The team found that UQ heads achieved state-of-the-art performance in claim-level hallucination detection across different domains and languages. Why it matters: This approach offers a more efficient and accurate method for identifying hallucinations, improving the reliability and trustworthiness of language models in various applications.
Liangming Pan from UCSB presented research on building reliable generative AI agents by integrating symbolic representations with LLMs. The neuro-symbolic strategy combines the flexibility of language models with precise knowledge representation and verifiable reasoning. The work covers Logic-LM, ProgramFC, and learning from automated feedback, aiming to address LLM limitations in complex reasoning tasks. Why it matters: Improving the reliability of LLMs is crucial for high-stakes applications in finance, medicine, and law within the region and globally.