Data Sheet 1_Emotional prompting amplifies disinformation generation in AI large language models.docx by Rasita Vinay (21006911)

“…Introduction<p>The emergence of artificial intelligence (AI) large language models (LLMs), which can produce text that closely resembles human-written content, presents both opportunities and risks. …”

GPT-4 results in decreased error rate for all tasks with increasing complexity when compared to GPT-3.5-turbo. by Jacqueline A. Jansen (14894276)

Feasibility of AI-powered assessment scoring: Can large language models replace human raters? by Michael Jaworski III (22156096)

“…<p><b>Objective:</b> To assess the feasibility, accuracy, and reliability of using ChatGPT-4.5 (early-access), a large language model (LLM), for automated scoring of Brief International Cognitive Assessment for Multiple Sclerosis (BICAMS) protocols. …”

<b>Supporting data for manuscript</b> "<b>Voluntary locomotion induces an early and remote hemodynamic decrease in the large cerebral veins</b>" by Kira Shaw (18796168)

“…The locomotion values (traces and metrics) are in arbitrary units with larger integers representing a greater displacement of the spherical treadmill, the hemodynamic (Hbt) values (traces and metrics) are a percentage change from the normalised baseline (prior to stimulus presentation), and the corresponding time series vector is presented in seconds. …”

Presentation 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip by Yan Cong (1491478)

Data Sheet 1_Tracking priming-induced language recovery in aphasia with pre-trained language models.zip by Yan Cong (1491478)

Penalty conversions yield large practical decreases, but robustness and generalizability of result are limited by data quality and sample selection. by Ryan J. Treves (13527735)

The PRAME-AS knockout cells showed a decrease in migration, proliferation, stemness, and viability. by Zahra Hosseininia (22265113)

Analysis of errors of the AI model on accuracy and decision times for different tasks during the retrospective reader study. (a) by Kerol Djoumessi (21349992)

Table 1_Effect of decreased suspended sediment content on chlorophyll-a in Dongting Lake, China.docx by Le Zhang (88249)

“…The reduction in SSC may influence chlorophyll-a (Chl-a) concentrations in water, thereby further affecting the aquatic ecological environment. …”

Data from: Colony losses of stingless bees increase in agricultural areas, but decrease in forested areas by Malena Sibaja Leyton (18400983)

A novel RNN architecture to improve the precision of ship trajectory predictions by Martha Dais Ferreira (18704596)

“…This research proposes a new RNN architecture that decreases the prediction error up to 50% for cargo vessels when compared to the OU model. …”

The reduced virulence of Δalta1 mutants is not primarily due to a decrease in growth. by Shuhuan Zhang (748003)

Innovation and night light in large and small cities. by Saul Estrin (8629173)

Geographical distribution of large cities and small cities. by Saul Estrin (8629173)

“…The Figure reveals two patterns: 1) the maximum level of innovation is higher in large cities (2.53) than in small cities (2.02); 2) among large cities in <b>a</b>, innovation levels in general decrease with nightlight density. …”

Incorporating a social responsibility goal in the prompt causes overleverage in utilities (A) and decreases risk of low ESG rating (B) (Study 3). by Philipp Winder (21615570)

Data Sheet 1_Large language models for closed-library multi-document query, test generation, and evaluation.docx by Claire Randolph (19747105)

“…Knowledge tests need to be generated on new material and existing tests revised, tracking knowledge base updates. Large Language Models (LLMs) provide a framework for artificial intelligence-assisted knowledge acquisition and continued learning. …”

ActAs and CoT prompt strategies do not result in decreased error rate for tasks with increasing complexity. by Jacqueline A. Jansen (14894276)

Self-correction prompt strategy results in decreased error rate for all tasks with increasing complexity. by Jacqueline A. Jansen (14894276)

fileCont prompt strategy results in decreased error rate for some tasks with increasing complexity. by Jacqueline A. Jansen (14894276)