The Distinguished Lecture Series, hosted by the School of Computing and Data Science (CDS), brings leading scholars from around the world to share their cutting-edge research and insights in the fields of computer science, data science, artificial intelligence, and statistics.

We are privileged to host Dr Xin Luna Dong, Principal Scientist at Meta Reality Labs, as a distinguished speaker in our Distinguished Lecture Series. Dr Dong will deliver a thought-provoking lecture entitled “Providing Factual Information with Dual Neural Knowledge.”

Speaker:

Dr. Xin Luna Dong, Principal Scientist, Meta Reality Labs 

Date:

30 October 2025 (Thursday)

Time:

11:00 am – 12:00 nn

Venue:

HW312, Haking Wong Building, The University of Hong Kong

Abstract:
For decades, multiple research communities—including Databases, Information Retrieval, Natural Language Processing, Data Mining, and AI—have pursued the mission of delivering the right information at the right time. These efforts span web search, data integration, knowledge graphs, and question answering. Recent advancements in Large Language Models (LLMs) have brought remarkable progress in language understanding and generation, reshaping approaches across all these fronts. Yet, limitations such as factual inaccuracies and hallucinations restrict their suitability for building knowledgeable and trustworthy assistants.

This talk introduces the Dual Neural Knowledge framework, which distinguishes between two complementary forms of knowledge: internalized knowledge, encoded in LLM parameters, and external symbolic knowledge, dynamically accessed through Retrieval-Augmented Generation (RAG). We present methods for integrating knowledge graphs, semi-structured data, and text sources to improve factuality, and describe how smooth transitions between the two forms enable seamless and synergistic knowledge use. We will share our techniques, findings, and future directions, highlighting how this work builds upon and extends decades of research toward trustworthy intelligent systems.

Biography:

Xin Luna Dong is a Principal Scientist at Meta Wearables AI, where she leads the Agentic AI efforts for building trustworthy and personalized assistants on wearable devices. Previously, she spent over a decade advancing knowledge graph technology, including the Amazon Product Graph and the Google Knowledge Graph. She is co-author of Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases and Big Data Integration. She is an ACM Fellow and IEEE Fellow, recognized for “significant contributions to knowledge graph construction and data integration.” She was named an ACM Fellow and an IEEE Fellow for “significant contributions to knowledge graph construction and data integration”, awarded the VLDB Women in Database Research Award and VLDB Early Career Research Contribution Award, and invited as an ACM Distinguished Speaker. She serves in the PVLDB advisory committee, was a member of the VLDB endowment, a PC co-chair for KDD’2022 ADS track, WSDM’2022, VLDB’2021, and Sigmod’2018.

All are welcome to attend.