Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to mitigate. We argue the relevance of exploring methods which are completely ignorant of the presence of any bias, but are capable of identifying and mitigating them. Furthermore, we propose using Bayesian neural networks with a predictive uncertainty-weighted loss function to dynamically identify potential bias in individual training samples and to weight them during training. We find a positive correlation between samples subject to bias and higher epistemic uncertainties. Finally, we show the method has potential to mitigate visual bias on a bias benchmark dataset and on a real-world face detection problem, and we consider the merits and weaknesses of our approach.

Graph anomaly detection (GAD) is increasingly crucial in various applications, ranging from financial fraud detection to fake news detection. However, current GAD methods largely overlook the fairness problem, which might result in discriminatory decisions skewed toward certain demographic groups defined on sensitive attributes (e.g., gender, religion, ethnicity, etc.). This greatly limits the applicability of these methods in real-world scenarios in light of societal and ethical restrictions. To address this critical gap, we make the first attempt to integrate fairness with utility in GAD decision-making. Specifically, we devise a novel DisEntangle-based FairnEss-aware aNomaly Detection framework on the attributed graph, named DEFEND. DEFEND first introduces disentanglement in GNNs to capture informative yet sensitive-irrelevant node representations, effectively reducing societal bias inherent in graph representation learning. Besides, to alleviate discriminatory bias in evaluating anomalous nodes, DEFEND adopts a reconstruction-based anomaly detection, which concentrates solely on node attributes without incorporating any graph structure. Additionally, given the inherent association between input and sensitive attributes, DEFEND constrains the correlation between the reconstruction error and the predicted sensitive attributes. Our empirical evaluations on real-world datasets reveal that DEFEND performs effectively in GAD and significantly enhances fairness compared to state-of-the-art baselines. To foster reproducibility, our code is available at https://github.com/AhaChang/DEFEND.

Synthetic tabular data generation with differential privacy is a crucial problem to enable data sharing with formal privacy. Despite a rich history of methodological research and development, developing differentially private tabular data generators that can provide realistic synthetic datasets remains challenging. This paper introduces DP-LLMTGen -- a novel framework for differentially private tabular data synthesis that leverages pretrained large language models (LLMs). DP-LLMTGen models sensitive datasets using a two-stage fine-tuning procedure with a novel loss function specifically designed for tabular data. Subsequently, it generates synthetic data through sampling the fine-tuned LLMs. Our empirical evaluation demonstrates that DP-LLMTGen outperforms a variety of existing mechanisms across multiple datasets and privacy settings. Additionally, we conduct an ablation study and several experimental analyses to deepen our understanding of LLMs in addressing this important problem. Finally, we highlight the controllable generation ability of DP-LLMTGen through a fairness-constrained generation setting.

Cross-validation is a common method for estimating the predictive performance of machine learning models. In a data-scarce regime, where one typically wishes to maximize the number of instances used for training the model, an approach called "leave-one-out cross-validation" is often used. In this design, a separate model is built for predicting each data instance after training on all other instances. Since this results in a single test data point available per model trained, predictions are aggregated across the entire dataset to calculate common rank-based performance metrics such as the area under the receiver operating characteristic or precision-recall curves. In this work, we demonstrate that this approach creates a negative correlation between the average label of each training fold and the label of its corresponding test instance, a phenomenon that we term distributional bias. As machine learning models tend to regress to the mean of their training data, this distributional bias tends to negatively impact performance evaluation and hyperparameter optimization. We show that this effect generalizes to leave-P-out cross-validation and persists across a wide range of modeling and evaluation approaches, and that it can lead to a bias against stronger regularization. To address this, we propose a generalizable rebalanced cross-validation approach that corrects for distributional bias. We demonstrate that our approach improves cross-validation performance evaluation in synthetic simulations and in several published leave-one-out analyses.

This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. We explore algorithmic methods and metrics to assess LLM performance, identify weaknesses, and guide development towards more trustworthy applications. Key evaluation metrics include Perplexity Measurement, NLP metrics (BLEU, ROUGE, METEOR, BERTScore, GLEU, Word Error Rate, Character Error Rate), Zero-Shot and Few-Shot Learning Performance, Transfer Learning Evaluation, Adversarial Testing, and Fairness and Bias Evaluation. We introduce innovative approaches like LLMMaps for stratified evaluation, Benchmarking and Leaderboards for competitive assessment, Stratified Analysis for in-depth understanding, Visualization of Blooms Taxonomy for cognitive level accuracy distribution, Hallucination Score for quantifying inaccuracies, Knowledge Stratification Strategy for hierarchical analysis, and Machine Learning Models for Hierarchy Generation. Human Evaluation is highlighted for capturing nuances that automated metrics may miss. These techniques form a framework for evaluating LLMs, aiming to enhance transparency, guide development, and establish user trust. Future papers will describe metric visualization and demonstrate each approach on practical examples.

The integration of Large Language Models (LLMs) into healthcare diagnostics offers a promising avenue for clinical decision-making. This study outlines the development of a novel method for zero-shot/few-shot in-context learning (ICL) by integrating medical domain knowledge using a multi-layered structured prompt. We also explore the efficacy of two communication styles between the user and LLMs: the Numerical Conversational (NC) style, which processes data incrementally, and the Natural Language Single-Turn (NL-ST) style, which employs long narrative prompts. Our study systematically evaluates the diagnostic accuracy and risk factors, including gender bias and false negative rates, using a dataset of 920 patient records in various few-shot scenarios. Results indicate that traditional clinical machine learning (ML) models generally outperform LLMs in zero-shot and few-shot settings. However, the performance gap narrows significantly when employing few-shot examples alongside effective explainable AI (XAI) methods as sources of domain knowledge. Moreover, with sufficient time and an increased number of examples, the conversational style (NC) nearly matches the performance of ML models. Most notably, LLMs demonstrate comparable or superior cost-sensitive accuracy relative to ML models. This research confirms that, with appropriate domain knowledge and tailored communication strategies, LLMs can significantly enhance diagnostic processes. The findings highlight the importance of optimizing the number of training examples and communication styles to improve accuracy and reduce biases in LLM applications.

Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy (Our code and dataset are available at https://github.com/zhliu0106/probing-lm-data).

Graph Neural Networks (GNNs) have been widely used in node classification tasks, such as advertising recommendation [15], social network anomaly detection [34], etc. However, these GNN models typically assume that the training and test graph data are drawn from the same distribution, which does not always hold in practice. In real-world graph data, sample selection bias [8, 12] as well as graph construction techniques [27, 43] often brings distribution shifts between training nodes and test nodes. For instance, In WebKB [26] datasets, web pages (nodes) and categories (labels) are heavily affected by the university they originate from, leading to distribution shifts among nodes drawn from different universities. Therefore, in order to enhance the practical validity of GNNs, it is of paramount importance to deal with distribution shifts on graph data. To address the distribution shift problem in node classification, recent works [18, 36, 32, 37, 23] borrow the idea of invariant learning methods from the literature of out-of-distribution (OOD) generalization and adopt them on graph-structured data. Invariant learning [1, 19] stems from the causal inference literature, and now becomes one of the key approaches to solving OOD problems on graphs. The core concept is to identify invariant features with stable prediction mechanisms across different environments, thereby mitigating performance degradation under distribution shifts. And most of the works in this line directly apply existing invariant learning algorithms to graph-level classification tasks (major) [18, 32, 23, 41] and node classification tasks (minor) [36, 38].

The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination, i.e. the benchmark data is used for training. In this work, we propose a holistic method named Polarized Augment Calibration (PAC) along with a new to-be-released dataset to detect the contaminated data and diminish the contamination effect. PAC extends the popular MIA (Membership Inference Attack) -- from machine learning community -- by forming a more global target at detecting training data to Clarify invisible training data. As a pioneering work, PAC is very much plug-and-play that can be integrated with most (if not all) current white- and black-box LLMs. By extensive experiments, PAC outperforms existing methods by at least 4.5%, towards data contamination detection on more 4 dataset formats, with more than 10 base LLMs. Besides, our application in real-world scenarios highlights the prominent presence of contamination and related issues.

Chronic cough disorders are widespread and challenging to assess because they rely on subjective patient questionnaires about cough frequency. Wearable devices running Machine Learning (ML) algorithms are promising for quantifying daily coughs, providing clinicians with objective metrics to track symptoms and evaluate treatments. However, there is a mismatch between state-of-the-art metrics for cough counting algorithms and the information relevant to clinicians. Most works focus on distinguishing cough from non-cough samples, which does not directly provide clinically relevant outcomes such as the number of cough events or their temporal patterns. In addition, typical metrics such as specificity and accuracy can be biased by class imbalance. We propose using event-based evaluation metrics aligned with clinical guidelines on significant cough counting endpoints. We use an ML classifier to illustrate the shortcomings of traditional sample-based accuracy measurements, highlighting their variance due to dataset class imbalance and sample window length. We also present an open-source event-based evaluation framework to test algorithm performance in identifying cough events and rejecting false positives. We provide examples and best practice guidelines in event-based cough counting as a necessary first step to assess algorithm performance with clinical relevance.