10.1k citations
- The University of SydneyAU198 papers
- Centre for Quantum Computation and Communication TechnologyAU120 papers
- UNSW SydneyAU97 papers
- Australian National UniversityAU88 papers
- Tsinghua UniversityCN80 papers
- Commonwealth Scientific and Industrial Research OrganisationAU75 papers
- Chinese Academy of SciencesCN74 papers
- Macquarie UniversityAU68 papers
- The University of MelbourneAU50 papers
- Data61AU43 papers
- ARC Centre of Excellence for Transformative Meta-Optical SystemsAU41 papers
- Nanyang Technological UniversitySG41 papers
1,714 papers
Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
Runsong Jia, Zhen Fang, Mengjia Wu +2
Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detect…
Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering
Runsong Jia, Mengjia Wu, Ying Ding +2
Academic question answering requires reasoning over heterogeneous scholarly graphs, where queries range from simple attribute lookups to multi-hop inference across author--paper--v…
The Tool-to-Entity Threshold: Parasocial Dynamics of Personalised AI Agents in Shared Social Spaces
Leonardo Borges, Asif Q. Gill
As AI agents acquire names, avatars, phone numbers, and persistent personalities, they increasingly inhabit the same messaging platforms and group conversations as the humans they…
MammoMix: Leveraging Mixture of Experts for Robust Mammogram Breast Detection
Dinh Tan Nguyen, Hoang Quan Dang, Chen Zhang +1
Breast lesion detection in mammography remains a challenging task due to variations in image quality, lesion appearance, and population demographics across datasets. While current…
When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse
Yingtao Ren, Ziyi Zhao, Yiwei Fu +3
Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial doc…
iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integration
Xiaowei Jiang, Daniel Leong, Beining Cao +5
Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain their reas…