Margrét V. Bjarnadóttir

Krithika Ramesh, Daniel Smolyak, Zihao Zhao et al.

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the risks of privacy violations in the development and deployment of AI systems in high-stakes domains. Realizing this potential, however, requires principled consistent evaluations of synthetic data across multiple dimensions: its utility in downstream systems, the fairness of these systems, the risk of privacy leakage, general distributional differences from the source text, and qualitative feedback from domain experts. SynthTextEval allows users to conduct evaluations along all of these dimensions over synthetic data that they upload or generate using the toolkit's generation module. While our toolkit can be run over any data, we highlight its functionality and effectiveness over datasets from two high-stakes domains: healthcare and law. By consolidating and standardizing evaluation metrics, we aim to improve the viability of synthetic text, and in-turn, privacy-preservation in AI development.

Daniel Smolyak, Arshana Welivita, Margrét V. Bjarnadóttir et al.

Objective. Demographic groups are often represented at different rates in medical datasets. These differences can create bias in machine learning algorithms, with higher levels of performance for better-represented groups. One promising solution to this problem is to generate synthetic data to mitigate potential adverse effects of non-representative data sets. Methods. We build on recent advances in LLM-based synthetic data generation to create a pipeline where the synthetic data is generated separately for each demographic group. We conduct our study using MIMIC-IV and Framingham "Offspring and OMNI-1 Cohorts" datasets. We prompt GPT4-Turbo to create group-specific data, providing training examples and the dataset context. An exploratory analysis is conducted to ascertain the quality of the generated data. We then evaluate the utility of the synthetic data for augmentation of a training dataset in a downstream machine learning task, focusing specifically on model performance metrics across groups. Results. The performance of GPT4-Turbo augmentation is generally superior but not always. In the majority of experiments our method outperforms standard modeling baselines, however, prompting GPT-4-Turbo to produce data specific to a group provides little to no additional benefit over a prompt that does not specify the group. Conclusion. We developed a method for using LLMs out-of-the-box to synthesize group-specific data to address imbalances in demographic representation in medical datasets. As another "tool in the toolbox", this method can improve model fairness and thus health equity. More research is needed to understand the conditions under which LLM generated synthetic data is useful for non-representative medical data sets.

Margret Bjarnadottir, Louiqa Raschid

The objective of this paper is to explore how financial big data and machine learning methods can be applied to model and understand financial products. We focus on residential mortgage backed securities, resMBS, which were at the heart of the 2008 US financial crisis. These securities are contained within a prospectus and have a complex waterfall payoff structure. Multiple financial institutions form a supply chain to create prospectuses. To model this supply chain, we use unsupervised probabilistic methods, particularly dynamic topics models (DTM), to extract a set of features (topics) reflecting community formation and temporal evolution along the chain. We then provide insight into the performance of the resMBS securities and the impact of the supply chain through a series of increasingly comprehensive models. First, models at the security level directly identify salient features of resMBS securities that impact their performance. We then extend the model to include prospectus level features and demonstrate that the composition of the prospectus is significant. Our model also shows that communities along the supply chain that are associated with the generation of the prospectuses and securities have an impact on performance. We are the first to show that toxic communities that are closely linked to financial institutions that played a key role in the subprime crisis can increase the risk of failure of resMBS securities.