grant

Discovery Projects - Grant ID: DP260104188 [ 2026-01-01 - 2028-12-31 ]

Research Grant

[Cite as https://purl.org/au-research/grants/arc/DP260104188]

Researchers: Dr Estrid He (Chief Investigator) ,  Jeffrey Chan (Chief Investigator) ,  Jenny Zhang (Chief Investigator) ,  Erik Cambria (Partner Investigator)

Brief description Reduce hallucination in large language models via knowledge-based reasoning. This project aims to address the critical challenge of hallucination -- a phenomenon where generative AI models produce information that appears plausible but is factually incorrect -- with a focus on news fact-checking. This project expects to advance knowledge in detecting and mitigating hallucinations by developing innovative techniques for integrating external factual knowledge into AI models. Expected outcomes of this project include a suite of innovative techniques to enhance AI models' capability to reason and generate grounded information for complex fact checking tasks. This should provide significant benefits, such as improved reliability for generative AI systems and more effective combat against misinformation at scale.

Funding Amount $598,708

Funding Scheme Discovery Projects

View this grant in the ARC Data Portal

Click to explore relationships graph
Identifiers
Viewed: [[ro.stat.viewed]]
ACN 633 798 857