ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters
This addresses the need for more adaptive and efficient inference-time adaptation in large language models, though it appears incremental as an enhancement to existing low-rank adaptation techniques.
The paper tackles the problem of fixed-weight LLMs' inability to adapt dynamically to real-world data variability during inference by introducing ChameleonLLM, which uses batch-aware clustering and on-the-fly low-rank updates to achieve significant performance gains over conventional LoRA methods.
Recent advances in large language models (LLMs) have shown remarkable performance across diverse tasks. However, these models are typically deployed with fixed weights, which limits their ability to adapt dynamically to the variability inherent in real-world data during inference. This paper introduces ChameleonLLM, a novel framework that enables inference-time adaptation of LLMs by leveraging batch-aware clustering and on-the-fly generation of low-rank updates. Unlike traditional fine-tuning approaches such as Low-Rank Adaptation (LoRA) or methods that rely on a fixed set of pre-learned uniforms (changeable masks), our method dynamically generates adaptive modifications to the decoder weights based on the aggregated statistics of clustered batches. By intelligently grouping similar inputs and computing context-aware low-rank updates via a hyper-network, ChameleonLLM achieves significant performance gains, outperforming conventional LoRA methods while eliminating the overhead of maintaining multiple expert models. Our experiments highlight the potential of our approach to serve as a versatile and highly adaptive solution for language model inference. ChameleonLLM is open-sourced to ensure the reproducibility of our experiments: https://anonymous.4open.science/r/ChamaleonLLM/