Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge
Provides a fully local, task-agnostic method to overcome LLM performance bottlenecks on specialized tasks without requiring supervision or distillation.
SKR adapts LLMs to non-generative tasks by re-expressing their intrinsic knowledge, achieving over 40% improvement in Recall@1 for retrieval, 76% latency reduction in detection, and 33% AUPRC increase in anomaly detection, surpassing leading retrieval models by 12.6% on MMDocRAG.
While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constrains performance on specialized, non-generative tasks. We attribute this performance bottleneck to the LLMs' knowledge expression mechanism, rather than to deficiencies in knowledge acquisition. To address this, we propose Self-Knowledge Re-expression (SKR), a novel, task-agnostic adaptation method. SKR transforms the LLM's output from generic token generation to highly efficient, task-specific expression. SKR is a fully local method that uses only unannotated data, requiring neither human supervision nor model distillation. Experiments on a large financial document dataset demonstrate substantial improvements: over 40% in Recall@1 for information retrieval tasks, over 76% reduction in object detection latency, and over 33% increase in anomaly detection AUPRC. Our results on the MMDocRAG dataset surpass those of leading retrieval models by at least 12.6%.