Self Knowledge Re-expression: A Fully Local Method for Adapting LLMs to Tasks Using Intrinsic Knowledge

TL;DR

The paper introduces Self-Knowledge Re-expression (SKR), a local, unsupervised method that adapts LLMs for specialized tasks by transforming their output mechanism, leading to significant performance improvements.

Contribution

SKR is a novel, fully local adaptation technique that enhances LLMs for specific tasks without supervision or distillation, addressing knowledge expression limitations.

Findings

Over 40% improvement in Recall@1 for info retrieval

76% reduction in object detection latency

33% increase in anomaly detection AUPRC

Abstract

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%.