Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …

Increasingly larger datasets have become a standard ingredient to advancing the state-of-
the-art in NLP. However, data quality might have already become the bottleneck to unlock …

In today's AI-driven world, understanding model behavior is becoming more important than
ever. While libraries abound for doing so via traditional XAI methods, the domain of …

Deep Neural Nets (DNNs) have become a pervasive tool for solving many emerging
problems. However, they tend to overfit to and memorize the training set. Memorization is of …

Many training data attribution (TDA) methods aim to estimate how a model's behavior would
change if one or more data points were removed from the training set. Methods based on …

Deep neural networks have achieved remarkable performance across various tasks when
supplied with large-scale labeled data. However, the collection of labeled data can be time …

Quantifying the impact of individual data samples on machine learning models is an open
research problem. This is particularly relevant when complex and high-dimensional …

Influence functions offer a robust framework for assessing the impact of each training data
sample on model predictions, serving as a prominent tool in data-centric learning. Despite …

Understanding memorisation in language models has practical and societal implications,
eg, studying models' training dynamics or preventing copyright infringements. Prior work …

The responses generated by Large Language Models (LLMs) can include sensitive
information from individuals and organizations, leading to potential privacy leakage. This …