Related papers: Singular Vectors of Attention Heads Align with Fea…

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Structured representations, such as Bags of Words, VLAD and Fisher Vectors, have proven highly effective to tackle complex visual recognition tasks. As such, they have recently been incorporated into deep architectures. However, while…

The success of large-scale contextual language models has attracted great interest in probing what is encoded in their representations. In this work, we consider a new question: to what extent contextual representations of concrete nouns…

This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…

Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing…

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…

Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. However, what remains unknown is which visual properties models actually converge on and…

Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing "under" or "behind" relationships between only two objects, pose significant…

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…

A key recent advance in face recognition models a test face image as a sparse linear combination of a set of training face images. The resulting sparse representations have been shown to possess robustness against a variety of distortions…

Neural network models have recently received heated research attention in the natural language processing community. Compared with traditional models with discrete features, neural models have two main advantages. First, they take…

A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature space (also known as attribute-value descriptions). A teacher…

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of…

This study addresses the problem of hallucinated span detection in the outputs of large language models. It has received less attention than output-level hallucination detection despite its practical importance. Prior work has shown that…

The potential of multimodal generative artificial intelligence (mAI) to replicate human grounded language understanding, including the pragmatic, context-rich aspects of communication, remains to be clarified. Humans are known to use…

Although large language models (LLMs) have demonstrated remarkable performance, the lack of transparency in their inference logic raises concerns about their trustworthiness. To gain a better understanding of LLMs, we conduct a detailed…

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language…

Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during…

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

Describing images with text is a fundamental problem in vision-language research. Current studies in this domain mostly focus on single image captioning. However, in various real applications (e.g., image editing, difference interpretation,…