Augmenting interpretable models with large language models during training

Citations Over TimeTop 10% of 2023 papers

Abstract

Recent large language models (LLMs), such as ChatGPT, have demonstrated remarkable prediction performance for a growing array of tasks. However, their proliferation into high-stakes domains and compute-limited settings has created a burgeoning need for interpretability and efficiency. We address this need by proposing Aug-imodels, a framework for leveraging the knowledge learned by LLMs to build extremely efficient and interpretable prediction models. Aug-imodels use LLMs during fitting but not during inference, allowing complete transparency and often a speed/memory improvement of greater than 1000x for inference compared to LLMs. We explore two instantiations of Aug-imodels in natural-language processing: Aug-Linear, which augments a linear model with decoupled embeddings from an LLM and Aug-Tree, which augments a decision tree with LLM feature expansions. Across a variety of text-classification datasets, both outperform their non-augmented, interpretable counterparts. Aug-Linear can even outperform much larger models, e.g. a 6-billion parameter GPT-J model, despite having 10,000x fewer parameters and being fully transparent. We further explore Aug-imodels in a natural-language fMRI study, where they generate interesting interpretations from scientific data.

Related Papers

• → ML interpretability: Simple isn't easy(2024)29 cited
• → Measures of Model Interpretability for Model Selection(2018)10 cited
• → Measuring Interpretability for Different Types of Machine Learning Models(2018)15 cited
• → Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability(2023)3 cited
• → ML Interpretability: Simple Isn't Easy(2022)2 cited