When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks
This work addresses the challenge of noisy regression tasks for practitioners using LLMs, offering an incremental improvement through embedding compression.
The paper tackles the problem of overfitting in LLM-based regression tasks by showing that compressing embeddings improves performance on noisy tasks like financial return prediction, with specific gains observed in such contexts, but reduces performance on tasks with high causal dependencies.
Large language models (LLMs) have shown remarkable success in language modelling due to scaling laws found in model size and the hidden dimension of the model's text representation. Yet, we demonstrate that compressed representations of text can yield better performance in LLM-based regression tasks. In this paper, we compare the relative performance of embedding compression in three different signal-to-noise contexts: financial return prediction, writing quality assessment and review scoring. Our results show that compressing embeddings, in a minimally supervised manner using an autoencoder's hidden representation, can mitigate overfitting and improve performance on noisy tasks, such as financial return prediction; but that compression reduces performance on tasks that have high causal dependencies between the input and target data. Our results suggest that the success of interpretable compressed representations such as sentiment may be due to a regularising effect.