Contrastive learning enhanced retrieval-augmented few-shot framework for multi-label patent classification. [PDF]
Zheng W, Li X, Cui G, Chen S.
europepmc +1 more source
ChatGPT for complex text evaluation tasks
Abstract ChatGPT and other large language models (LLMs) have been successful at natural and computer language processing tasks with varying degrees of complexity. This brief communication summarizes the lessons learned from a series of investigations into its use for the complex text analysis task of research quality evaluation.
Mike Thelwall
wiley +1 more source
Hyper-MDR: An open-world multimodal reasoning framework based on dynamic hypergraph and meta-strategy optimization. [PDF]
Shi J, Huang X, Yuan L.
europepmc +1 more source
Abstract Caste—an ascriptive social hierarchy in South Asia and its diaspora—is a globalized phenomenon. Recent caste‐based discrimination, particularly in technology companies and anti‐caste efforts to address it, has compelled academia, policy, and the technology industry to better understand contemporary mechanics of caste.
Nayana Kirasur, Britt Paris
wiley +1 more source
Integration of corpus linguistics and deep learning techniques for enhanced semantic-driven emotion detection on textual data. [PDF]
Al-Onazi BB +7 more
europepmc +1 more source
Delineating gender/sex‐related studies through bibliometric analysis
Abstract The multidisciplinary and socially grounded nature of Women's/Gender/Feminist Studies poses unique challenges for bibliometric analysis, as it extends beyond conventional disciplinary boundaries. This paper makes three key contributions: (1) We propose a novel retrieval method for constructing a corpus of scholarly documents in research areas ...
Natsumi S. Shokida +2 more
wiley +1 more source
Higher-Order Logical Reasoning in Preschool Children: Evidence from Intonation and Quantifier Scope. [PDF]
Sauerland U, Sugawara A, Yatsushiro K.
europepmc +1 more source
When AI outputs become documents: Documentation activity in human–AI dialogue
Abstract Large language models (LLMs) generate texts that increasingly circulate as documents in knowledge infrastructures, yet their documentary status remains theoretically underdetermined. Unlike traditional documents, LLM outputs lack identifiable authorship, stable provenance, or testimonial grounding.
Sascha Donner
wiley +1 more source
A hybrid contrastive graph neural network framework for fake news and hate speech detection using content and user interaction signals. [PDF]
Nivedita VS, Banu AB.
europepmc +1 more source
ABSTRACT Auditory mismatch responses—mismatch negativity (MMN) and mismatch fields (MMF)—are well established electrophysiological markers of automatic auditory discrimination supported by short‐term sensory memory. These responses, typically elicited using passive oddball paradigms, are increasingly used to investigate sensory and language processing ...
Sara Cacciato‐Salcedo +4 more
wiley +1 more source

