Related papers: CiteBench: A benchmark for Scientific Citation Tex…

Planning is a fundamental capability for large language models (LLMs) because such complex tasks require models to coordinate goals, constraints, resources, and long-term consequences into executable and verifiable solutions. Existing…

With the rapid growth in the number of scientific publications, year after year, it is becoming increasingly difficult to identify quality authoritative work on a single topic. Though there is an availability of scientometric measures which…

Workload traces from cloud data warehouse providers reveal that standard benchmarks such as TPC-H and TPC-DS fail to capture key characteristics of real-world workloads, including query repetition and string-heavy queries. In this paper, we…

Communicating new research ideas involves highlighting similarities and differences with past work. Authors write fluent, often long sections to survey the distinction of a new paper with related work. In this work we model generating…

Effective scientific communication depends on accurate citations that validate sources and guide readers to supporting evidence. Yet academic literature faces mounting challenges: semantic citation errors that misrepresent sources,…

Hierarchical Text Classification (HTC) is a natural language processing task with the objective to classify text documents into a set of classes from a structured class hierarchy. Many HTC approaches have been proposed which attempt to…

Many theories of scientific and technological progress imagine science as an iterative, developmental process periodically interrupted by innovations which disrupt and restructure the status quo. Due to the immense societal value created by…

Citations in scholarly work serve the essential purpose of acknowledging and crediting the original sources of knowledge that have been incorporated or referenced. Depending on their surrounding textual context, these citations are used for…

Citation parsing is fundamental for search engines within academia and the protection of intellectual property. Meticulous extraction is further needed when evaluating the similarity of documents and calculating their citation impact.…

We present an overview of the SCIDOCA 2025 Shared Task, which focuses on citation discovery and prediction in scientific documents. The task is divided into three subtasks: (1) Citation Discovery, where systems must identify relevant…

Layout-guided text-to-image models offer greater control over the generation process by explicitly conditioning image synthesis on the spatial arrangement of elements. As a result, their adoption has increased in many computer vision…

Classifying journals or publications into research areas is an essential element of many bibliometric analyses. Classification usually takes place at the level of journals, where the Web of Science subject categories are the most popular…

Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly simplistic, test cases often lack rigor, and end-to-end…

To broaden the dissemination of scientific knowledge to diverse audiences, it is desirable for scientific document summarization systems to simultaneously control multiple attributes such as length and empirical focus. However, existing…

The capability of large language models to handle long-context information is crucial across various real-world applications. Existing evaluation methods often rely either on real-world long texts, making it difficult to exclude the…

Over the last four decades, the way knowledge is created in academia has transformed dramatically: research teams have grown larger, scholars draw from ever-wider pools of prior work, and the most influential discoveries increasingly emerge…

The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy and comprehensiveness, necessitating…

Digital Science's Dimensions is envisaged as a next-generation research and discovery platform for a better and more efficient access to cross-referenced scholarly publications, grants, patents, and clinical trials. As a new addition to the…

We introduce SciTrek, a diagnostic question-answering benchmark designed to probe long-context numerical reasoning in large language models (LLMs). Existing long-context benchmarks mostly focus on simple information retrieval, rely on…

The continuous growth of scientific literature brings innovations and, at the same time, raises new challenges. One of them is related to the fact that its analysis has become difficult due to the high volume of published papers for which…