Related papers: On the Size of $\exists$-Generalized Concepts
Measuring the similarity between patches in images is a fundamental building block in various tasks. Naturally, the patch-size has a major impact on the matching quality, and on the consequent application performance. Under the assumption…
In recent years, the field of generative artificial intelligence, particularly in the domain of image generation, has exerted a profound influence on society. Despite the capability of AI to produce images of high quality, the augmentation…
The highly influential framework of conceptual spaces provides a geometric way of representing knowledge. Instances are represented by points in a high-dimensional space and concepts are represented by regions in this space. In this…
Evaluating the factual consistency of automatically generated summaries is essential for the progress and adoption of reliable summarization systems. Despite recent advances, existing factuality evaluation models are not robust, being…
Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts. We study the problem of compositional generalization, which measures how well a…
This paper aims to generalize and unify classical criteria for comparisons of balanced lattice designs, including fractional factorial designs, supersaturated designs and uniform designs. We present a general majorization framework for…
Analogical reasoning is a powerful qualitative reasoning tool that enables humans to connect two situations, and to generalize their knowledge from familiar to novel situations. Cognitive Science research provides valuable insights into the…
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap. This hinders QA models from generalizing to under-represented samples such as…
How do transformer-based large language models (LLMs) store and retrieve knowledge? We focus on the most basic form of this task -- factual recall, where the model is tasked with explicitly surfacing stored facts in prompts of form `Fact:…
Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components. It is a key in human intelligence, but current neural networks generally lack such ability. This report…
Knowledge Discovery in Databases (KDD) aims to exploit the vast amounts of data generated daily across various domains of computer applications. Its objective is to extract hidden and meaningful knowledge from datasets through a structured…
The objectives of this research work which is intimately related to pattern discovery and management are threefold: (i) handle the problem of pattern manipulation by defining operations on patterns, (ii) study the problem of enriching and…
Recent advancements in large language models (LLMs) demonstrate strong potential for generating novel research ideas, yet such ideas often struggle with feasibility and effectiveness. In this paper, we investigate whether augmenting LLMs…
Using large language models (LMs) for query or document expansion can improve generalization in information retrieval. However, it is unknown whether these techniques are universally beneficial or only effective in specific settings, such…
In this paper, we revisit cognitive extent, originally defined as the number of unique phrases in a quota. We introduce Freshness and Informative Weighted Cognitive Extent (FICE), calculated based on two novel weighting factors, the…
We generalize many results concerning the tractability of SAT and #SAT on bounded treewidth CNF-formula in the context of Quantified Boolean Formulas (QBF). To this end, we start by studying the notion of width for OBDD and observe that the…
Most previous methods for text data augmentation are limited to simple tasks and weak baselines. We explore data augmentation on hard tasks (i.e., few-shot natural language understanding) and strong baselines (i.e., pretrained models with…
Semantic networks provide a useful tool to understand how related concepts are retrieved from memory. However, most current network approaches use pairwise links to represent memory recall patterns. Pairwise connections neglect higher-order…
Formal Concept Analysis makes the fundamental observation that any finite lattice $(L, \leq)$ is determined up to isomorphism by the restriction of the relation ${\leq} \subseteq L \times L$ to the set $J(L) \times M(L)$, where $J(L)$ is…
Recent advancements in image synthesis have enabled high-quality image generation and manipulation. Most works focus on: 1) conditional manipulation, where an image is modified conditioned on a given attribute, or 2) disentangled…