Exploring the Latest LLMs for Leaderboard Extraction
This work addresses the need for efficient automation in AI research by providing guidance on LLM performance for extracting structured data from papers, though it appears incremental as it focuses on comparing existing models on a specific task.
This paper tackled the problem of automating leaderboard information extraction from AI research articles by evaluating the efficacy of LLMs like Mistral 7B, Llama-2, GPT-4-Turbo, and GPT-4.o with different contextual inputs, finding significant insights into their strengths and limitations.
The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (Task, Dataset, Metric, Score) quadruples from research papers. The findings reveal significant insights into the strengths and limitations of each model and context type, providing valuable guidance for future AI research automation efforts.