A review of large language models and autonomous agents in chemistry

MC Ramos, C Collison, AD White - Chemical Science, 2024 - pubs.rsc.org
Large language models (LLMs) have emerged as powerful tools in chemistry, significantly
impacting molecule design, property prediction, and synthesis optimization. This review …

Deep learning in sentiment analysis: Recent architectures

T Abdullah, A Ahmet - ACM Computing Surveys, 2022 - dl.acm.org
Humans are increasingly integrated with devices that enable the collection of vast
unstructured opinionated data. Accurately analysing subjective information from this data is …

Is ChatGPT a general-purpose natural language processing task solver?

C Qin, A Zhang, Z Zhang, J Chen, M Yasunaga… - arXiv preprint arXiv …, 2023 - arxiv.org
Spurred by advancements in scale, large language models (LLMs) have demonstrated the
ability to perform a variety of natural language processing (NLP) tasks zero-shot--ie, without …

Latent diffusion for language generation

J Lovelace, V Kishore, C Wan… - Advances in …, 2024 - proceedings.neurips.cc
Diffusion models have achieved great success in modeling continuous data modalities such
as images, audio, and video, but have seen limited use in discrete domains such as …

Nougat: Neural optical understanding for academic documents

L Blecher, G Cucurull, T Scialom, R Stojnic - arXiv preprint arXiv …, 2023 - arxiv.org
Scientific knowledge is predominantly stored in books and scientific journals, often in the
form of PDFs. However, the PDF format leads to a loss of semantic information, particularly …

Menstrual irregularities and vaginal bleeding after COVID-19 vaccination reported to v-safe active surveillance, USA in December, 2020–January, 2022: an …

KK Wong, CM Heilig, A Hause, TR Myers… - The Lancet Digital …, 2022 - thelancet.com
Background Anecdotal reports of menstrual irregularities after receiving COVID-19 vaccines
have been observed in post-authorisation and post-licensure monitoring. We aimed to …

Ares: An automated evaluation framework for retrieval-augmented generation systems

J Saad-Falcon, O Khattab, C Potts… - arXiv preprint arXiv …, 2023 - arxiv.org
Evaluating retrieval-augmented generation (RAG) systems traditionally relies on hand
annotations for input queries, passages to retrieve, and responses to generate. We …

Unraveling energy justice in NYC urban buildings through social media sentiment analysis and transformer deep learning

M Ashayeri, N Abbasabadi - Energy and Buildings, 2024 - Elsevier
This study explores the intricate relationship between human sentiment on social media
data, herein tweet posts on X platform, urban building characteristics, and the socio-spatial …

The implementation of the cognitive theory of multimedia learning in the design and evaluation of an AI educational video assistant utilizing large language models

R AlShaikh, N Al-Malki, M Almasre - Heliyon, 2024 - cell.com
Abstract The integration of Artificial Intelligence (AI) holds immense potential for
revolutionizing education; especially, in contexts where multimodal learning experiences …

Self-supervised pretraining and transfer learning enable\titlebreak flu and covid-19 predictions in small mobile sensing datasets

MA Merrill, T Althoff - Conference on Health, Inference, and …, 2023 - proceedings.mlr.press
Detailed mobile sensing data from phones and fitness trackers offer an opportunity to
quantify previously unmeasurable behavioral changes to improve individual health and …