Example of the prompts used to query the tested Large Language Models (LLMs). by Nicola Luigi Bragazzi (6931424)

Strengthening assessment integrity in the era of generative AI: evidence from a large-scale study by Liz Hardie (22277602)

“…This large-scale empirical study at a UK university, based on 590 student and 354 AI-generated answers, provides evidence on markers’ ability to detect the GenAI scripts and whether some assessment types are more robust than others against GenAI misuse. …”

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. …”

Brief summary highlighting the study methology. a) AI Tool Development and Pediatric Repurposing: The AI tool was originally trained and validated using a large dataset of adult ch... by Prerana Agarwal (21781515)

Subjects:

Bibliometric methods for identifying AI-assisted papers by Andrew Gray (10234100)

Table 1_Association between the atherogenic index of plasma and risk of large-artery atherosclerotic ischemic stroke.xlsx by Wen Zhong (425650)

“…</p>Results<p>Individuals with consistently high levels of AIP were at increased risk of developing LAA, and this risk increased progressively with increasing levels of AIP. …”

Findings from ANOVA and post-hoc analyses comparing the average performance of the Large Language Models against dietetics and English students. by Nicola Luigi Bragazzi (6931424)

Findings from ANOVA and post-hoc analyses comparing the average performance of the Large Language Models against male and female participants. by Nicola Luigi Bragazzi (6931424)

Findings from ANOVA and post-hoc analyses comparing the average performance of the Large Language Models against participants of various education groups. by Nicola Luigi Bragazzi (6931424)

Findings from ANOVA and post-hoc analyses comparing the average performance of the Large Language Models against participants of various age groups. by Nicola Luigi Bragazzi (6931424)

Table 2_ePWV as a scalable risk factor for large-scale glaucoma screening: evidence from a national Chinese cohort.docx by Yupeng Xu (6787604)

Table 1_ePWV as a scalable risk factor for large-scale glaucoma screening: evidence from a national Chinese cohort.docx by Yupeng Xu (6787604)

AI augmentation in evidence synthesis workflows. by Alaa Al Khourdajie (13843729)

Subjects:

Findings from ANOVA and post-hoc analyses comparing the average performance of the Large Language Models against participants of various health status groups. by Nicola Luigi Bragazzi (6931424)

Data Sheet 1_Conversational AI agent for precision oncology: AI-HOPE-WNT integrates clinical and genomic data to investigate WNT pathway dysregulation in colorectal cancer.docx by Ei-Wen Yang (149486)

“…Additionally, patients under 50 with APC-mutant primary tumors showed worse survival (p = 0.031) and increased mutation prevalence.</p>Conclusion<p>AI-HOPE-WNT is the first dedicated AI platform for WNT pathway analysis in CRC. …”

Supplementary file 1_Swedish Medical LLM Benchmark: development and evaluation of a framework for assessing large language models in the Swedish medical domain.pdf by Birger Moëll (21699569)

“…Introduction<p>We present the Swedish Medical LLM Benchmark (SMLB), an evaluation framework for assessing large language models (LLMs) in the Swedish medical domain.…”

HDECO: A method for Decreasing energy and cost by using virtual machine migration by considering hybrid parameters by Arash GhorbanniaDelavar (22563696)

“…<h2>Summary</h2><p dir="ltr">This research introduces <b>HDECO</b> (Hybrid Decreasing Energy and Cost Optimization) — a method designed to reduce both energy consumption and execution cost in cloud datacenters through intelligent virtual machine migration. …”

Opening the Black Box(es) by Charles Pence (99065)

“…<p dir="ltr">A talk which explores challenges for contemporary work in digital humanities stemming from the increasing use of generative large language models.</p>…”

Conceptual integration of AI-generated products into the IPCC assessment workflow. by Alaa Al Khourdajie (13843729)

Subjects:

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)