ExperienceWeaver: Optimizing Small-sample Experience Learning for LLM-based Clinical Text Improvement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911413176369152 |
|---|---|
| author | Xiao, Ziyan Zhu, Yinghao Peng, Liang Yu, Lequan |
| author_facet | Xiao, Ziyan Zhu, Yinghao Peng, Liang Yu, Lequan |
| contents | Clinical text improvement is vital for healthcare efficiency but remains difficult due to limited high-quality data and the complex constraints of medical documentation. While Large Language Models (LLMs) show promise, current approaches struggle in small-sample settings: supervised fine-tuning is data-intensive and costly, while retrieval-augmented generation often provides superficial corrections without capturing the reasoning behind revisions. To address these limitations, we propose ExperienceWeaver, a hierarchical framework that shifts the focus from data retrieval to experience learning. Instead of simply recalling past examples, ExperienceWeaver distills noisy, multi-dimensional feedback into structured, actionable knowledge. Specifically, error-specific Tips and high-level Strategies. By injecting this distilled experience into an agentic pipeline, the model learns "how to revise" rather than just "what to revise". Extensive evaluations across four clinical datasets demonstrate that ExperienceWeaver consistently improves performance, surpassing state-of-the-art models such as Gemini-3 Pro in small-sample settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00740 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ExperienceWeaver: Optimizing Small-sample Experience Learning for LLM-based Clinical Text Improvement Xiao, Ziyan Zhu, Yinghao Peng, Liang Yu, Lequan Computation and Language Artificial Intelligence Clinical text improvement is vital for healthcare efficiency but remains difficult due to limited high-quality data and the complex constraints of medical documentation. While Large Language Models (LLMs) show promise, current approaches struggle in small-sample settings: supervised fine-tuning is data-intensive and costly, while retrieval-augmented generation often provides superficial corrections without capturing the reasoning behind revisions. To address these limitations, we propose ExperienceWeaver, a hierarchical framework that shifts the focus from data retrieval to experience learning. Instead of simply recalling past examples, ExperienceWeaver distills noisy, multi-dimensional feedback into structured, actionable knowledge. Specifically, error-specific Tips and high-level Strategies. By injecting this distilled experience into an agentic pipeline, the model learns "how to revise" rather than just "what to revise". Extensive evaluations across four clinical datasets demonstrate that ExperienceWeaver consistently improves performance, surpassing state-of-the-art models such as Gemini-3 Pro in small-sample settings. |
| title | ExperienceWeaver: Optimizing Small-sample Experience Learning for LLM-based Clinical Text Improvement |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00740 |