Can ChatGPT Predict Article Retraction Based on Twitter Mentions?
Twitter mentions can predict article retraction, with ChatGPT showing superior performance compared to other methods.
Efficient Token Reduction for Large Multimodal Models: PruMerge Study
Efficiently reducing visual tokens while maintaining model performance is crucial for large multimodal models.
Closing the Information Gap in Unidentified Anomalous Phenomena (UAP) Studies
Legitimizing UAP studies through interdisciplinary research.
TableLlama: Developing Open Generalist Models for Tables
Developing open-source generalist models for table-based tasks through instruction tuning.
Insights from a Focus Group Moderator
Understanding the dynamics and challenges of moderating focus groups.
Automating Systematic Literature Review with Multi-AI Agents
The author introduces a multi-AI agent model to automate the systematic literature review process, leveraging Large Language Models (LLMs) for efficiency and accuracy.
Analyzing Large Language Models on Dynamic Graphs
The authors propose to evaluate Large Language Models' spatial-temporal understanding abilities on dynamic graphs for the first time, introducing the LLM4DyG benchmark and a new prompting technique, DST2.
Exploring Large Language Model Datasets: A Comprehensive Survey
The author explores the critical role of datasets in advancing Large Language Models, categorizing them into five perspectives and highlighting challenges and future directions.