Results 41 to 50 of about 287,230 (232)

To model human linguistic prediction, make LLMs less superhuman

Trends in Cognitive Sciences
When we read, we make predictions about upcoming words; these predictions influence our reading behavior. The success of large language models (LLMs), which, like humans, make predictions about upcoming words, has motivated their use as models of human linguistic prediction. Surprisingly, in the last few years, as LLMs' ability to predict the next word
Byung-Doh Oh, Tal Linzen
openaire   +2 more sources

StackingNet: Collective Inference Across Independent AI Foundation Models

Advanced Science, EarlyView.
ABSTRACT Artificial intelligence (AI) built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems remain isolated and cannot readily share their capabilities. Coordinating the complementary strengths of independently developed, black‐box foundation models is essential for trustworthy ...
Siyang Li, Chenhao Liu, Dongrui Wu, Zhigang Zeng, Lieyun Ding   +4 more
wiley   +1 more source

Deep Learning Prediction of O‐Glycopeptide Tandem Mass Spectra Enhances O‐Glycoproteomics

Advanced Science, EarlyView.
DeepGPO integrates Transformer and graph neural networks with tailored training strategies, including data augmentation, loss re‐weighting, and pre‐training, to achieve high‐quality O‐glycopeptide MS/MS spectra prediction. The predicted MS/MS spectra are used to localize O‐glycosylation sites from HCD MS/MS data, enhancing O‐glycoproteomics analysis ...
Yu Zong, Yuxin Wang, Liang Qiao
wiley   +1 more source

Genetic relationship between Kaili and Pamona languages: a historical comparative linguistics study

Cogent Arts & Humanities
Kaili and Pamona speakers are different language speaking communities living in the Central Sulawesi Province, Indonesia. This study aims to determine the genetic relationship of Kaili and Pamona languages by using lexicostatistics, glottochronology and ...
Dewi Khairiah, S. Fatinah, Joni Endardi, Nursyamsi, Dwi Atmawati   +4 more
semanticscholar   +1 more source

Large models of what? Mistaking engineering achievements for human linguistic agency

Language Sciences
In this paper we argue that key, often sensational and misleading, claims regarding linguistic capabilities of Large Language Models (LLMs) are based on at least two unfounded assumptions; the assumption of language completeness and the assumption of data completeness.
Abeba Birhane, Marek McGann
openaire   +2 more sources

CLRe: A Synergistic Dual‐Engine Framework for One‐Step Retrosynthesis Prediction

Advanced Science, EarlyView.
CLRe uses a contrastive difficulty score to order pretrained seq2seq fine‐tuning for retrosynthesis. Reaction embeddings define the ranking score, and a cumulative easy‐to‐hard schedule expands from the easiest subset to the full training set while earlier examples remain active.
Tianhao Su, Xitao Wang, Musen Li, Guanhua Qin, Shunbo Hu, Tong‐Yi Zhang   +5 more
wiley   +1 more source

The Societal Relevance of Linguistic Humanities: Case Studies in Education, Translation, and Forensic Communication

Bodhi international journal of research in humanities, arts and science
Applied Linguistics is an interdisciplinary research discipline which brings together theoretical linguistics and practice and aims to find solutions to practical language problems in different contexts.
M. M. Geetha, Dr. P. Preethi
semanticscholar   +1 more source

Tumor‐Derived Exosomal circAP2B1 Induces M2 Macrophage Polarization by Enhancing Mitochondrial Homeostasis to Promote Esophageal Squamous Cell Carcinoma Progression

Advanced Science, EarlyView.
ESCC‐derived exosomal circAP2B1 promotes tumor progression by reprogramming mitochondrial metabolism via the ESRRA/KPNA1/MFN2 axis to induce M2 polarization of macrophages. ABSTRACT Esophageal squamous cell carcinoma (ESCC) remodels the immunosuppressive tumor microenvironment via exosome‐mediated intercellular communication.
Yiru Wang, Gang Feng, Youyu Wang, Ruihao Liang, Haixia Pan, Kai Lei   +5 more
wiley   +1 more source

CoSP: Reconfigurable Metamaterial Inverse Design via Contrastive Pretrained Large Language Model

Advanced Science, EarlyView.
In this work, CoSP (contrastive multi‐state pretrain), an intelligent inverse design method for reconfigurable metamaterials based on a contrastive pretrained large language model, is proposed. Numerical experiments demonstrate that CoSP can design reconfigurable metamaterial structures for multi‐state, multi‐band optical responses, showing great ...
Shujie Yang, Yuqi Zhang, Xuzhe Zhao, Yansong Tang, Kaichen Dong   +4 more
wiley   +1 more source

Claiming Relevance for Social Science and the Humanities: Relevance Expressions Across Methodological Divides

Minerva
This article addresses the issue of how Social Science and Humanities (SSH) researchers frame and argue relevance, where there are no explicit expectations to do so.
Tomas Hellström, Merle Jacob
semanticscholar   +1 more source