Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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%.

Mengyu Wang, Xiaoying Zhi, Zhiyi Li, Robin Schmucker, Shay B. Cohen, Tiejun Ma, Fran Silavong• 2026

Related benchmarks

TaskDatasetResultRank
Anomaly DetectionTAD (test)
Overall AUC99.1
23
Text-to-Text RetrievalMMDocRAG (test)
MRR67.4
19
Object DetectionT_OD
mIoU72.6
14
Text-to-Image RetrievalMMDocRAG (test)
MRR69.1
13
Information RetrievalMMDocRAG
Recall@1087.7
10
Anomaly DetectionCUB-200 2011
Accuracy0.986
6
Object DetectionCUB-200-2011 (test)
IoU69.2
6
Text-to-Image RetrievalDocVQA 2020 (test)
MRR0.931
2
Text-to-Image RetrievalSciMMIR (test)
MRR56.2
2
Showing 9 of 9 rows

Other info

Follow for update