AI 2025: Advances in Artificial Intelligence: 38th Australasian Joint Conference on Artificial Intelligence, AI 2025, Canberra, ACT, Australia, December 1–5, 2025, Proceedings, Part IMiaomiao Liu, Xin Yu, Chang Xu, Yiliao Song This two-volume set LNAI 16370-16371 constitutes the refereed proceedings of the 38th Australasian Joint Conference on Artificial Intelligence, AI 2025, held in Canberra, ACT, Australia, during December 1–5, 2025. The 73 full papers presented together with 1 short papers were carefully reviewed and selected from 152 submissions. They were organized in following topical section: Part I : Language and Foundation Models and Knowledge Representation and Data Mining, Part II : Learning Algorithms, Computer Vision, AI for Healthcare and Reinforcement Learning and Robotics. |
Contents
| 3 | |
| 15 | |
Enhancing RAG System Performance Through Semantic Layout Chunking | 28 |
Automating Perdurant MetaProperty Assignment Using GPT4 | 40 |
Evaluating Large Language Models for RealWorld Engineering Tasks | 54 |
Generation of Ethical Rules Using Large Language Models | 67 |
Large Language Models Imitate Logical Reasoning but at What Cost? | 80 |
A LexiconEnhanced Approach to ParameterEfficient FineTuning for Financial News Sentiment Classification | 97 |
On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems | 260 |
Comparing Calibration with Conditional Mean Operators | 274 |
Investigating Political Bias of Large Language Models | 288 |
A Framework for Trustworthy AI Adoption | 301 |
Knowledge Representation and Data Mining | 308 |
Categorization Architecture with Predictive Reasoning and Alignment for UNSPSC | 311 |
DirectionAware Spectral Graph Embedding Learning via SVD and Transformer | 324 |
Predicting Generalization Error Under Graph Distribution Shifts via Parameter Discrepancy with Accumulated Gradient | 336 |
ConsistencyGuided OOD Detection with Pretrained VisionLanguage Models | 110 |
Towards Robust Continual TestTime Adaptation via Replay Prompt for CLIP | 122 |
Trustworthy and Explainable AI | 134 |
Probabilistic Lipschitzness and the Stable Rank for Measuring XAI Model Robustness | 137 |
GraphBased Integrated Gradients for Explaining Graph Neural Networks | 150 |
Assessing Algorithmic Fairness in Socioeconomic Predictions Using Australian Census Data | 163 |
IoT Intrusion Detection with XAIDriven Feature Refinement for Enhanced Multiclass Edge Classification | 177 |
PrivacyPreserving Human Pose Estimation Using Random HighFrequency Channel Combinations | 191 |
Do They Understand Them? An Updated Evaluation on Nonbinary Pronoun Handling in Large Language Models | 204 |
Concept Control for LLM Safety Using Radial Basis Function Representations | 220 |
An Empirical Study of LLM Robustness in Code Vulnerability Detection | 233 |
RequirementsBased Explainability for Multiagent Systems | 246 |
Predicting Graph Structure via Adapted Flux Balance Analysis | 351 |
A Clustered Additive LoRA Framework for Robust and Personalized Federated Learning | 364 |
DROWCULA | 378 |
NoiseRobust Topology Estimation of 2D Image Data via Neural Networks and Persistent Homology | 392 |
A Multimodal Fire Spread Prediction Framework | 405 |
A Deep Learning Pipeline for Marine Acoustic Intelligence | 417 |
Weather Forecasting System Four Seasons in One Day and Shelter Suggestion for Sydney and Melbourne and Canberra | 432 |
Proactive Air Quality Forecasting and Health Alert System for Melbourne | 444 |
Solving Partial Graph Matching as a Stable Matching Problem | 458 |
| 471 | |
Other editions - View all
AI 2025: Advances in Artificial Intelligence: 38th Australasian Joint ... Miaomiao Liu,Xin Yu,Chang Xu,Yiliao Song No preview available - 2025 |
Common terms and phrases
accuracy adaptation agent algorithms alignment analysis applications approach architecture Artificial Intelligence arXiv preprint Australia AutoEncoder automated baseline benchmark bias calibration cFedLAD chunking CKCE classification clustering complex Computer Vision context dataset demonstrate denotes directed graph distribution domain edge embedding encoder enhance error ethical evaluation explanations fine-tuning forecasting framework gender global GradNorm graph neural networks IEEE improve inference input integration Jaccard index labels large language models Lipschitz Lipschitz constant LLMs LoRA machine learning matrix meta-property methods metrics multi-modal neural networks node noise OOD detection optimal outputs parameters partial graph matching performance pipeline prediction prompt pronoun proposed query real-world reasoning representation retrieval robustness samples scenarios score Sect semantic semi-supervised learning similar classes social media stable matching stable rank strategies structure supervised learning Table tasks tion Transformer UNSPSC updates validation vector West Nile virus zero-shot Zhang