Related papers: Approximate Attributions for Off-the-Shelf Siamese…

The truthfulness of existing explanation methods in authentically elucidating the underlying model's decision-making process has been questioned. Existing methods have deviated from faithfully representing the model, thus susceptible to…

Many natural language processing and information retrieval problems can be formalized as the task of semantic matching. Existing work in this area has been largely focused on matching between short texts (e.g., question answering), or…

Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance sampling (IS). Recently, mixture models with negative coefficients, called subtractive…

Existing work has analyzed the representational capacity of the transformer architecture by means of formal models of computation. However, the focus so far has been on analyzing the architecture in terms of language \emph{acceptance}. We…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world applications. Our work proposes a novel approach to interpreting…

Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level features can become harder to recover as the residual stream is repeatedly…

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the…

Intelligent voice assistants, such as Apple Siri and Amazon Alexa, are widely used nowadays. These task-oriented dialogue systems require a semantic parsing module in order to process user utterances and understand the action to be…

Trustworthy answer content is abundant in many high-resource languages and is instantly accessible through question answering systems, yet this content can be hard to access for those that do not speak these languages. The leap forward in…

Transformer is a powerful tool for many natural language tasks which is based on self-attention, a mechanism that encodes the dependence of other tokens on each specific token, but the computation of self-attention is a bottleneck due to…

Riemannian diffusion models draw inspiration from standard Euclidean space diffusion models to learn distributions on general manifolds. Unfortunately, the additional geometric complexity renders the diffusion transition term inexpressible…

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural…

Understanding the inner workings of machine learning models like Transformers is vital for their safe and ethical use. This paper provides a comprehensive analysis of a one-layer Transformer model trained to perform n-digit integer…

Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training…

Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features…

As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In practice, new input data tend to come without target labels. Then, state-of-the-art techniques model input data distributions…

To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of existing attribution methods lies in efficiently and accurately identifying the relationships among…