large language models

Simulated responses from large language models are weak proxies for human economic preferences across 74 countries

From Bytecode to Heritage: AI-Assisted Restoration of Java Executable Artworks

Executable works produced in Java in the late 1990s are threatened by the disappearance of applets and the obsolescence of their software interfaces. This article presents an exploratory study of their restoration from bytecode and surviving assets, without access to the original source code. The protocol combines two...

Strong Solvers, Leaky Tutors: Evaluating Answer Leakage in LLM Math Tutors

Educational digital libraries may grant large language model (LLM) tutors access to worked solutions, but access to repository content should not automatically authorize a model to reveal final answers. This study evaluates whether LLM tutors can leverage private solution context to generate pedagogical hints without d...

Energy constraints in large scale artificial intelligence and insights from human cognition for efficient large language models

Abstract Large-scale artificial intelligence (AI) systems, especially large language models (LLMs), face growing constraints related to energy use, power delivery, memory traffic, experimentation, and infrastructure capacity. These pressures are often studied separately, which makes it difficult to understand how they...

Can Large Language Models Identify Technical Terms in Documents Like Human Annotators?

Processing technical terms in documents is essential for digital libraries and knowledge organisation, supporting applications such as scholarly search, information retrieval, and domain terminology construction. While document-level term identification, a sub-task of automatic term extraction (ATE), has been tackled a...

Enhanced language-guided robotic grasping via a synergized VLM-based two-stage decoupled policy

Editorial: Understanding conscious experiences during sleep

The sleeping brain hosts a spectrum of subjective experiences, ranging from fleeting hypnagogic images and simple thoughts to vivid, full-fledged dreams and lucid dreaming. The works published in this Research Topic present novel methodological and conceptual approaches to studying these experiences. Contributions span...

Decision models can offload structured clinical tasks from large language models

Decision models like Jev read text and return probabilities, categories, or ordinal levels, with confidence scores for the latter two, at a fraction of large language models' (LLMs) cost. We explored how Jev could be integrated into clinical workflows for all these output types: mortality risk estimation, categorical C...

Mapping the Molecular Universe

The success of large-language-models highlighted the importance of datasets, whose quantity, quality, and diversity dictate the accuracy and creativity of artificial intelligence (AI) systems in learning and inferring. However, in scientific domains, such datasets required for domain-specific AI/machine-learning (ML)...

Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles

Extracting hypotheses and their supporting statistical evidence from full-text scientific articles is central to the synthesis of empirical findings, but remains difficult due to document length and the distribution of scientific arguments across sections of the paper. We study a sequential full-text extraction setting...

Translation and NER

Abstract The Prize Papers collection includes a wealth of early modern logbooks in various languages, posing challenges for researchers when trying to obtain place and time information, e.g. to visualize shipping routes. Our approach is to use machine translation in order to enhance access to named entity recognition (...

Can LLMs Identify Advisor-Advisee Relationships in Coauthorship Network Based on Publication Metadata?

Identifying advisor–advisee relationships from bibliographic metadata has largely relied on coauthorship network signals. This paper evaluates whether large language models (LLMs) can infer advising relationships from publication metadata alone and whether they can improve on a locally trained probabilistic ranking mod...