Related papers: Google Scholar Metrics 2014: a low cost bibliometr…
Evaluating the open-form textual responses generated by Large Language Models (LLMs) typically requires measuring the semantic similarity of the response to a (human generated) reference. However, there is evidence that current semantic…
The article reveals the experience of organizing blended learning for geography students using Google Classroom, and discloses its potential uses in the study of geography. For the last three years, the authors have tested such inclass and…
We prove two complexity results about the H-index concerned with the Google scholar merge operation on one's scientific articles. The results show that, although it is hard to merge one's articles in an optimal way, it is easy to merge them…
Rs4rs is a web application designed to perform semantic search on recent papers from top conferences and journals related to Recommender Systems. Current scholarly search engine tools like Google Scholar, Semantic Scholar, and ResearchGate…
Educational materials such as survey articles in specialized fields like computer science traditionally require tremendous expert inputs and are therefore expensive to create and update. Recently, Large Language Models (LLMs) have achieved…
The ever-growing corpus of scientific literature presents significant challenges for researchers with respect to discovery, management, and annotation of relevant publications. Traditional platforms like Semantic Scholar, BibSonomy, and…
This paper investigates Large Language Models (LLMs) ability to assess the economic soundness and theoretical consistency of empirical findings in spatial econometrics. We created original and deliberately altered "counterfactual" summaries…
This paper deploys bibliometric indices and semantic techniques for understanding to what extent research grants are likely to impact publications, research direction, and co-authorship rate of principal investigators. The novelty of this…
With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome this problem, we introduce a new task of disentangled paper summarization, which…
Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quantity of parallel…
Identifying the research topics that best describe the scope of a scientific publication is a crucial task for editors, in particular because the quality of these annotations determine how effectively users are able to discover the right…
Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data…
The environmental impact of software is gaining increasing attention as the demand for computational resources continues to rise. In order to optimize software resource consumption and reduce carbon emissions, measuring and evaluating…
Traditional graph centrality measures effectively quantify node importance but fail to capture the structural uniqueness of multi-scale connectivity patterns -- critical for understanding network resilience and function. This paper…
Although citation-based indicators are widely used for research evaluation, they are not useful for recently published research, reflect only one of the three common dimensions of research quality, and have little value in some social…
Social media has become integrated into the fabric of the scholarly communication system in fundamental ways: principally through scholarly use of social media platforms and the promotion of new indicators on the basis of interactions with…
Despite the central importance of research papers to scientific progress, they can be difficult to read. Comprehension is often stymied when the information needed to understand a passage resides somewhere else: in another section, or in…
Large language models (LLMs) assisted literature retrieval may lead to erroneous references, but these errors have not been rigorously quantified. Therefore, we quantitatively assess errors in reference retrieval of widely used free-version…
Previous research has shown that journal article quality ratings from the cloud based Large Language Model (LLM) families ChatGPT and Gemini and the medium sized open weights LLM Gemma3 27b correlate moderately with expert research quality…
The main goal of this research is to analyze the web structure and performance of units and services belonging to U.S. academic libraries in order to check their suitability for webometric studies. Our objectives include studying their…