Large Language Models for Scientific Information Extraction: An Empirical Study for Virology
This provides a practical tool for scientists to navigate complex scientific literature, though it is incremental as it applies existing LLM methods to a new domain.
The paper tackled the problem of extracting structured scientific information from dense academic texts, specifically in virology, by using large language models (LLMs) for automated summarization, and found that a finetuned FLAN-T5 model with 1000x fewer parameters than GPT-davinci was competitive for the task.
In this paper, we champion the use of structured and semantic content representation of discourse-based scholarly communication, inspired by tools like Wikipedia infoboxes or structured Amazon product descriptions. These representations provide users with a concise overview, aiding scientists in navigating the dense academic landscape. Our novel automated approach leverages the robust text generation capabilities of LLMs to produce structured scholarly contribution summaries, offering both a practical solution and insights into LLMs' emergent abilities. For LLMs, the prime focus is on improving their general intelligence as conversational agents. We argue that these models can also be applied effectively in information extraction (IE), specifically in complex IE tasks within terse domains like Science. This paradigm shift replaces the traditional modular, pipelined machine learning approach with a simpler objective expressed through instructions. Our results show that finetuned FLAN-T5 with 1000x fewer parameters than the state-of-the-art GPT-davinci is competitive for the task.