Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods apply fixed compression rates, over-compressing simple queries or under-compressing complex ones. We propose Adaptive Context Compression for RAG (ACC-RAG), a framework that dynamically adjusts compression rates based on input complexity, optimizing inference efficiency without sacrificing accuracy. ACC-RAG combines a hierarchical compressor (for multi-granular embeddings) with a context selector to retain minimal sufficient information, akin to human skimming. Evaluated on Wikipedia and five QA datasets, ACC-RAG outperforms fixed-rate methods and matches/unlocks over 4 times faster inference versus standard RAG while maintaining or improving accuracy.

Water balance models (WBMs) are often employed to understand regional hydrologic cycles over various time scales. Most WBMs, however, are physically-based, and few employ state-of-the-art statistical methods to reconcile independent input measurement uncertainty and bias. Further, few WBMs exist for large lakes, and most large lake WBMs perform additive accounting, with minimal consideration towards input data uncertainty. Here, we introduce a framework for improving a previously developed large lake statistical water balance model (L2SWBM). Focusing on the water balances of Lakes Superior and Michigan-Huron, we demonstrate our new analytical framework, identifying L2SWBMs from 26 alternatives that adequately close the water balance of the lakes with satisfactory computation times compared with the prototype model. We expect our new framework will be used to develop water balance models for other lakes around the world.