10 citations · 42 across the 19 of their papers we have counts for
22 papers
Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create More
Deng Pan, Joe Germino, Yihong Ma +4
Thinking in reasoning language models (RLMs) has been subject to debate on whether it resolves or amplifies bias. Prior works have shown competing conclusions in both directions. U…
Adaptive Traffic Camouflage: Causal and Resource-Aware Defense Against IoT Fingerprinting
Daniel Adu Worae, Spyridon Mastorakis, Nuno Moniz +1
Encryption hides IoT payloads, but traffic shape can still reveal device identity through packet sizes, timing, direction, and packetization. We present Adaptive Traffic Camouflage…
LLMs4All: A Review of Large Language Models Across Academic Disciplines
Yanfang Ye, Zheyuan Zhang, Tianyi Ma +26
Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown t…
Context Attribution with Multi-Armed Bandit Optimization
Deng Pan, Keerthiram Murugesan, Ting Hua +2
Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable and trustworthy retrieval-augment…
Intersectional Divergence: Measuring Fairness in Regression
Joe Germino, Nuno Moniz, Nitesh V. Chawla
Fairness in machine learning research is commonly framed in the context of classification tasks, leaving critical gaps in regression. In this paper, we propose a novel approach to…
NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning
Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le +9
Diet plays a critical role in human health, yet tailoring dietary reasoning to individual health conditions remains a major challenge. Nutrition Question Answering (QA) has emerged…
Class-Aware Contrastive Optimization for Imbalanced Text Classification
Grigorii Khvatskii, Nuno Moniz, Khoa Doan +1
The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed s…
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
Jiayi Ye, Yanbo Wang, Yue Huang +9
LLM-as-a-Judge has been widely utilized as an evaluation method in various benchmarks and served as supervised rewards in model training. However, despite their excellence in many…
LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs
Yujun Zhou, Jingdong Yang, Yue Huang +12
Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language mo…
BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks
Anna Sokol, Elizabeth Daly, Michael Hind +4
Large language models (LLMs) are powerful tools capable of handling diverse tasks. Comparing and selecting appropriate LLMs for specific tasks requires systematic evaluation method…
Empowering Open Data Sharing for Social Good: A Privacy-Aware Approach
Tânia Carvalho, Luís Antunes, Cristina Costa +1
The Covid-19 pandemic has affected the world at multiple levels. Data sharing was pivotal for advancing research to understand the underlying causes and implement effective contain…
Automated Privacy-Preserving Techniques via Meta-Learning
Tânia Carvalho, Nuno Moniz, Luís Antunes
Sharing private data for learning tasks is pivotal for transparent and secure machine learning applications. Many privacy-preserving techniques have been proposed for this task aim…
Synthetic Data Outliers: Navigating Identity Disclosure
Carolina Trindade, Luís Antunes, Tânia Carvalho +1
Multiple synthetic data generation models have emerged, among which deep learning models have become the vanguard due to their ability to capture the underlying characteristics of…
AnyLoss: Transforming Classification Metrics into Loss Functions
Doheon Han, Nuno Moniz, Nitesh V Chawla
Many evaluation metrics can be used to assess the performance of models in binary classification tasks. However, most of them are derived from a confusion matrix in a non-different…
Fast Explanations via Policy Gradient-Optimized Explainer
Deng Pan, Nuno Moniz, Nitesh Chawla
The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depe…
Conformalized Selective Regression
Anna Sokol, Nuno Moniz, Nitesh Chawla
Should prediction models always deliver a prediction? In the pursuit of maximum predictive performance, critical considerations of reliability and fairness are often overshadowed,…
Are we making much progress? Revisiting chemical reaction yield prediction from an imbalanced regression perspective
Yihong Ma, Xiaobao Huang, Bozhao Nan +4
The yield of a chemical reaction quantifies the percentage of the target product formed in relation to the reactants consumed during the chemical reaction. Accurate yield predictio…
A Three-Way Knot: Privacy, Fairness, and Predictive Performance Dynamics
Tânia Carvalho, Nuno Moniz, Luís Antunes
As the frontier of machine learning applications moves further into human interaction, multiple concerns arise regarding automated decision-making. Two of the most critical issues…
Class-Imbalanced Learning on Graphs: A Survey
Yihong Ma, Yijun Tian, Nuno Moniz +1
The rapid advancement in data-driven research has increased the demand for effective graph data analysis. However, real-world data often exhibits class imbalance, leading to poor p…
Differentially-Private Data Synthetisation for Efficient Re-Identification Risk Control
Tânia Carvalho, Nuno Moniz, Luís Antunes +1
Protecting user data privacy can be achieved via many methods, from statistical transformations to generative models. However, all of them have critical drawbacks. For example, cre…
Survey on Privacy-Preserving Techniques for Data Publishing
Tânia Carvalho, Nuno Moniz, Pedro Faria +1
The exponential growth of collected, processed, and shared microdata has given rise to concerns about individuals' privacy. As a result, laws and regulations have emerged to contro…
Towards a Data Privacy-Predictive Performance Trade-off
Tânia Carvalho, Nuno Moniz, Pedro Faria +1
Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One o…