Reliable and Specialised LLMs (ReLLMS) Workshop

In recent years, Large Language Models (LLMs) have revolutionised fields like natural language processing, generating human-like text and solving complex tasks. However, the reliability of these models particularly in high-stakes or domain-specific application, remains a critical challenge.

This workshop will explore the unique issues related to the reliability of LLMs and delve into the potential of specialised LLMs tailored to specific industries or domains.

Participants will engage in discussions and hands-on activities designed to uncover the best practices for improving the robustness, trustworthiness, and domain-specific performance of LLMs.

• Reliability Challenges in LLMs: Biases, inaccuracies, adversarial attacks, and data limitations.
• Trustworthy AI and Privacy: How transparency can foster trust in LLM systems
• AI and Reliable LLM for detection of misinformation and disinformation 
• AI and Reliable LLM for breaking of echo chamber on social media and social networks.
• AI and Reliable LLM for fairness and social justice influenced by social opinions leaders. 
• Knowledge distillation for reliable AI and LLM
• Domain adaptation for reliable AI and LLM
• Specialised LLMs: How can we create domain-specific models that outperform general-purpose LLMs in certain areas?
• Testing and Evaluation: Approaches for measuring the reliability and effectiveness of specialised LLMs.
• Training and Fine-Tuning for Specific Applications: Healthcare, finance, law enforcement, etc.
• Ethical Concerns: Addressing transparency, accountability, and fairness in the use of LLMs in sensitive contexts.

Important Dates

• Paper submission: May 8, 2025
• Notification of acceptance: July 27, 2025
• Camera-ready deadline: August 10, 2025

Formatting Guidelines 

• Papers must be written in English and present unpublished contributions relevant to data mining and related fields. 
• Manuscripts must adhere strictly to the LNAI (Lecture Notes in Artificial Intelligence) format. Templates and details on the LNCS style can be found on Springer’s Author Instructions webpage. 
• Papers should NOT exceed 15 pages in LNAI format. 
• All submissions will undergo a double-blind peer review process, meaning: Author identities and affiliations are concealed from reviewers. 
• Submissions must be suitably blinded, omitting author and affiliation details. Accidental identification must be diligently avoided by both authors and reviewers. The author list provided at submission is final and cannot be altered post-submission. 
• Failure to adhere to these guidelines may result in desk rejection.

Submission Guidelines

• Authors are invited to submit original research papers, case studies, and technical reports aligned with the theme Reliable and Specialised LLMs. Submissions must follow the conference's formatting guidelines and be submitted through the CMT online submission system.
• When submitting your manuscript, please select the "Special Session Track" and choose the area "Special Session: Reliable and Specialised LLMs."

Submit your paper

Session Chairs

Professor Xue Li, The University of Queensland, Australia 

Professor Xue Li is a Professor in the School of Electrical Engineering and Computer Science at The University of Queensland (UQ) in Brisbane, Queensland, Australia. He is honoured as one of "the most powerful people in Australia" on Big Data by the Financial Review - the Power Issue 2015. His major areas of research interests and expertise include: Health Data Analytics, Data Mining, Social Computing, and Intelligent Web Information Systems.

Dr Priyanka Singh, The University of Queensland, Australia 

Priyanka Singh is a lecturer of cybersecurity at the University of Queensland, Australia. Prior to this, she worked as the assistant professor at the Dhirubhai Ambani Institute of Information and Communication Technology in Gujarat, India. She has a PhD in image forensics and earned prestigious postdoctoral fellowships from Dartmouth College and University at Albany in USA and Indian Institute of Technology Roorkee in India. Her research areas include cybersecurity, privacy preservation, and multimedia forensics.

Technical Committee

1. Guanfeng Liu, Macquarie University, Australia
2. Jia Wu, Macquarie University, Australia 
3. Yanjun Zhang, The University of Technology Sydney, Australia
4. Ling Chen, National Yang Ming Chiao Tung University, Taiwan 
5. Lin Yue, The University of Adelaide, Australia
6. Manoranjan Mohanty, Carnegie Mellon University, Qatar