Related papers: DIVINE: Diverse Influential Training Points for Da…

Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness in other stages in the ML pipeline. We contend that one…

Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the "value" of individual training datapoints have been proposed…

Bias in training datasets must be managed for various groups in classification tasks to ensure parity or equal treatment. With the recent growth in artificial intelligence models and their expanding role in automated decision-making,…

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning. How can we decide whether different treatments are reasonable or…

The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning…

Curriculum learning, a training technique where data is presented to the model in order of example difficulty (e.g., from simpler to more complex documents), has shown limited success for pre-training language models. In this work, we…

Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents,…

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current…

It is widely held that one cause of downstream bias in classifiers is bias present in the training data. Rectifying such biases may involve context-dependent interventions such as training separate models on subgroups, removing features…

As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users. Recently, researchers have shown that…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Selecting appropriate training data is crucial for effective instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced performance across a diverse range of tasks.…

As Text-to-Video (T2V) generation models continue to evolve, the complexity of video evaluation necessitates a fine-grained assessment across various axes. To address this, recent works have focused on developing Multidimensional Video…

Influence functions estimate the effect of removing a training point on a model without the need to retrain. They are based on a first-order Taylor approximation that is guaranteed to be accurate for sufficiently small changes to the model,…

The training of diffusion models is computationally intensive, making effective pre-training essential. However, real-world deployments often demand models of variable sizes due to diverse memory and computational constraints, posing…

Existing methods for measuring training sample influence on models only provide static, overall measurements, overlooking how sample influence changes during training. We propose Dynamic Influence Tracker (DIT), which captures the…

As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local…

Tabular data is one of the most common data storage formats behind many real-world web applications such as retail, banking, and e-commerce. The success of these web applications largely depends on the ability of the employed machine…

Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize to unseen…

Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through…