Abstract:Large language models (LLMs) have demonstrated their prowess in generating synthetic text and images; however, their potential for generating tabular data -- arguably the most common data type in business and scientific applications -- is largely underexplored. This paper demonstrates that LLMs, used as-is, or after traditional fine-tuning, are severely inadequate as synthetic table generators. Due to the autoregressive nature of LLMs, fine-tuning with random order permutation runs counter to the importance of modeling functional dependencies, and renders LLMs unable to model conditional mixtures of distributions (key to capturing real world constraints). We showcase how LLMs can be made to overcome some of these deficiencies by making them permutation-aware.
Abstract:Understanding key insights from full-text scholarly articles is essential as it enables us to determine interesting trends, give insight into the research and development, and build knowledge graphs. However, some of the interesting key insights are only available when considering full-text. Although researchers have made significant progress in information extraction from short documents, extraction of scientific entities from full-text scholarly literature remains a challenging problem. This work presents an automated End-to-end Research Entity Extractor called EneRex to extract technical facets such as dataset usage, objective task, method from full-text scholarly research articles. Additionally, we extracted three novel facets, e.g., links to source code, computing resources, programming language/libraries from full-text articles. We demonstrate how EneRex is able to extract key insights and trends from a large-scale dataset in the domain of computer science. We further test our pipeline on multiple datasets and found that the EneRex improves upon a state of the art model. We highlight how the existing datasets are limited in their capacity and how EneRex may fit into an existing knowledge graph. We also present a detailed discussion with pointers for future research. Our code and data are publicly available at https://github.com/DiscoveryAnalyticsCenter/EneRex.