Related papers: Stylized innovation: generating timelines by inter…
This study investigates the consequences of training language models on synthetic data generated by their predecessors, an increasingly prevalent practice given the prominence of powerful generative models. Diverging from the usual emphasis…
The landscape of interactive systems is shifting toward dynamic, generative experiences that empower users to explore and construct knowledge in real time. Yet, timelines -- a fundamental tool for representing historical and conceptual…
The problem of identifying common concepts in the sciences and deciding when new ideas have emerged is an open one. Metascience researchers have sought to formalize principles underlying stages in the life-cycle of scientific research,…
This paper presents an evolutionary algorithm for modeling the arrival dates of document streams, which is any time-stamped collection of documents, such as newscasts, e-mails, IRC conversations, scientific journals archives and weblog…
Graphic design is an effective language for visual communication. Using complex composition of visual elements (e.g., shape, color, font) guided by design principles and aesthetics, design helps produce more visually-appealing content. The…
Network representations can help reveal the behavior of complex systems. Useful information can be derived from the network properties and invariants, such as components, clusters or cliques, as well as from their changes over time. The…
The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise…
When we speak, write or listen, we continuously make predictions based on our knowledge of a language's grammar. Remarkably, children acquire this grammatical knowledge within just a few years, enabling them to understand and generalise to…
The increasing use of synthetic data generated by Large Language Models (LLMs) presents both opportunities and challenges in data-driven applications. While synthetic data provides a cost-effective, scalable alternative to real-world data…
Recent work has attempted to characterize the structure of semantic memory and the search algorithms which, together, best approximate human patterns of search revealed in a semantic fluency task. There are a number of models that seek to…
Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…
The rapid growth of web has resulted in vast volume of information. Information availability at a rapid speed to the user is vital. English language (or any for that matter) has lot of ambiguity in the usage of words. So there is no…
The application of semantic technologies to content on the web is, in many regards, important and urgent. Search engines, chatbots, intelligent personal assistants and other technologies increasingly rely on content published as semantic…
This paper presents a method of understanding the growth of global science as resulting from a mechanism of preferential attachment within networks. The paper seeks to contribute to the development of indicators of knowledge creation and…
Generalization is arguably the most important goal of statistical language modeling research. Publicly available benchmarks and papers published with an open-source code have been critical to advancing the field. However, it is often very…
Uncovering hidden symbolic laws from time series data, as an aspiration dating back to Kepler's discovery of planetary motion, remains a core challenge in scientific discovery and artificial intelligence. While Large Language Models show…
Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating its posterior at each step based on observed query-answer pairs.…
The paper tries to identify new emerging patterns in the context of technological progress. Just as industrialization is associated with rationalization, mechanization, and automation, the Internet age is associated with computer models,…
Meaning can be generated when information is related at a systemic level. Such a system can be an observer, but also a discourse, for example, operationalized as a set of documents. The measurement of semantics as similarity in patterns…
Technology adoption research aims to determine the reasons why and how individuals, corporations, and industries start using new technology. Furthermore, technology adoption itself is decomposed into underlying sub-processes which are…