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)

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)

“…<p>For all tasks, ophthalmologists’ accuracy is higher when the deep learning model makes the correct decision. …”

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)

Simple block slopes on proportion of risky decisions based on task. by Brooke H. Nancekivell (19949839)

Subjects:

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. …”

Network architectures for multi-agents task. by Hongjie Zhang (136127)

“…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …”

Regions of significance for the simple block slopes on proportion of risky decisions as a function of past-month nonsuicidal self-injury (NSSI) and task. by Brooke H. Nancekivell (19949839)

Subjects:

Time(s) and GFLOPs savings of single-agent tasks. by Hongjie Zhang (136127)

“…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …”

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

Variables making up each of the seven dimensions of the QoL Index. by Edmore Marinda (286299)

Scores vs Skip ratios on single-agent task. by Hongjie Zhang (136127)

“…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …”

Demographic and self-injury history characteristics for the sample. by Brooke H. Nancekivell (19949839)

Subjects:

Bivariate correlations and descriptive statistics for study variables. by Brooke H. Nancekivell (19949839)

Subjects:

Marginal means – Pooled across scenarios. by Mehdi Mourali (10170245)

“…A randomized conjoint experiment and a follow-up choice experiment revealed that support for the EIAs decreased sharply as their accuracy gap grew, although impact parity was prioritized more when ETAs produced large outcome discrepancies. …”

Decision-making deconstructed. by Jyotika Bahuguna (729510)

Win rate vs Skip ratios on multi-agents tasks. by Hongjie Zhang (136127)

“…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …”

Single agent and multi-agents tasks for <i>LazyAct</i>. by Hongjie Zhang (136127)

“…<div><p>Deep reinforcement learning has achieved significant success in complex decision-making tasks. However, the high computational cost of policies based on deep neural networks restricts their practical application. …”

Ventromedial PFC pattern-separates cue-task associations. by Guochun Yang (1329693)