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

There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of…

Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions. Besides flexibility and accuracy, a key benefit of…

Many recent self-supervised frameworks for visual representation learning are based on certain forms of Siamese networks. Such networks are conceptually symmetric with two parallel encoders, but often practically asymmetric as numerous…

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

The development of effective explainability tools for Transformers is a crucial pursuit in deep learning research. One of the most promising approaches in this domain is Layer-wise Relevance Propagation (LRP), which propagates relevance…

Transformers are widely deployed in large language models (LLMs), yet most models still fail on basic arithmetic tasks such as multidigit addition. In contrast, we show that small transformers trained from scratch can solve n-digit addition…

We propose a method of aligning a source image to a target image, where the transform is specified by a dense vector field. The two images are encoded as feature hierarchies by siamese convolutional nets. Then a hierarchy of aligner modules…

Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language…

A major bottleneck of standard auto-regressive large language models is that their inference process is inherently sequential, resulting in very long and costly inference times. To circumvent this, practitioners proposed a class of language…

The rapid developments of various machine learning models and their deployments in several applications has led to discussions around the importance of looking beyond the accuracies of these models. Fairness of such models is one such…

In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in…

Accuracy and individual fairness are both crucial for trustworthy machine learning, but these two aspects are often incompatible with each other so that enhancing one aspect may sacrifice the other inevitably with side effects of true bias…

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

A central problem in machine learning is often formulated as follows: Given a dataset $\{(x_j, y_j)\}_{j=1}^M$, which is a sample drawn from an unknown probability distribution, the goal is to construct a functional model $f$ such that…

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

LLMs can help humans working with long documents, but are known to hallucinate. Attribution can increase trust in LLM responses: The LLM provides evidence that supports its response, which enhances verifiability. Existing approaches to…

In this paper, we propose a new text recognition model based on measuring the visual similarity of text and predicting the content of unlabeled texts. First a Siamese convolutional network is trained with deep supervision on a labeled…

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential…

Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust…

Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text…