Publications (17)
Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
David Williams-King, Linh Le, Adam Oberman +1
As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have…
Leveraging Semantic Type Dependencies for Clinical Named Entity Recognition
Linh Le, Guido Zuccon, Gianluca Demartini +2
Previous work on clinical relation extraction from free-text sentences leveraged information about semantic types from clinical knowledge bases as a part of entity representations.…
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
Astha Mehta, Niruthiha Selvanayagam, Cedric Lam +10
An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts o…
Diagnosing Pathological Chain-of-Thought in Reasoning Models
Manqing Liu, David Williams-King, Ida Caspary +5
Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT reasoning may exhibit failure m…
A Multiple-Entanglement Routing Framework for Quantum Networks
Tu N. Nguyen, Kashyab J. Ambarani, Linh Le +2
Quantum networks are gaining momentum in finding applications in a wide range of domains. However, little research has investigated the potential of a quantum network framework to…
EEG-SSM: Leveraging State-Space Model for Dementia Detection
Xuan-The Tran, Linh Le, Quoc Toan Nguyen +2
State-space models (SSMs) have garnered attention for effectively processing long data sequences, reducing the need to segment time series into shorter intervals for model training…
Representation Engineering for Large-Language Models: Survey and Research Challenges
Lukasz Bartoszcze, Sarthak Munshi, Bryan Sukidi +6
Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new…
Efficient Embedding VNFs in 5G Network Slicing: A Deep Reinforcement Learning Approach
Linh Le, Tu N. Nguyen, Kun Suo +1
5G radio access network (RAN) slicing aims to logically split an infrastructure into a set of self-contained programmable RAN slices, with each slice built on top of the underlying…
CinPatent: Datasets for Patent Classification
Minh-Tien Nguyen, Nhung Bui, Manh Tran-Tien +2
Patent classification is the task that assigns each input patent into several codes (classes). Due to its high demand, several datasets and methods have been introduced. However, t…
Can ChatGPT Diagnose Alzheimer's Disease?
Quoc-Toan Nguyen, Linh Le, Xuan-The Tran +2
Can ChatGPT diagnose Alzheimer's Disease (AD)? AD is a devastating neurodegenerative condition that affects approximately 1 in 9 individuals aged 65 and older, profoundly impairing…
Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning
Isabella Luong, Joyee Chen, Arturs Kanepajs +5
Evaluating animal welfare reasoning in LLMs remains an open challenge despite rapid deployment in consumer and professional contexts where welfare considerations appear implicitly…
ReINTEL: A Multimodal Data Challenge for Responsible Information Identification on Social Network Sites
Duc-Trong Le, Xuan-Son Vu, Nhu-Dung To +8
This paper reports on the ReINTEL Shared Task for Responsible Information Identification on social network sites, which is hosted at the seventh annual workshop on Vietnamese Langu…
Deep Embedding Kernel
Linh Le, Ying Xie
In this paper, we propose a novel supervised learning method that is called Deep Embedding Kernel (DEK). DEK combines the advantages of deep learning and kernel methods in a unifie…
Federated Artificial Intelligence for Unified Credit Assessment
Minh-Duc Hoang, Linh Le, Anh-Tuan Nguyen +2
With the rapid adoption of Internet technologies, digital footprints have become ubiquitous and versatile to revolutionise the financial industry in digital transformation. This pa…
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
Linh Le, David Williams-King, Mohamed Amine Merzouk +2
Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerab…
Improving the clinical utility of lower-limb surface electromyography (sEMG) by quantifying and correcting for location changes in inter-session recordings
Fraser Douglas, Mona Pei, Quoc Sy Vu +2
Purpose: Surface electromyography (sEMG) can enable direct muscle activity measurement to support the recovery assessment of individuals with neurological and musculoskeletal disor…
Efficient Safety Alignment of Language Models via Latent Personality Traits
Mohamed Amine Merzouk, Nolan Smyth, Damiano Fornasiere +3
Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Latent Adversarial Training (LAT)…