RUIE: Retrieval-based Unified Information Extraction using Large Language Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912195759046656 |
|---|---|
| author | Liao, Xincheng Duan, Junwen Huang, Yixi Wang, Jianxin |
| author_facet | Liao, Xincheng Duan, Junwen Huang, Yixi Wang, Jianxin |
| contents | Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle to generalize to unseen tasks. We propose RUIE (Retrieval-based Unified Information Extraction), a framework that leverages in-context learning for efficient task generalization. RUIE introduces a novel demonstration selection mechanism combining LLM preferences with a keyword-enhanced reward model, and employs a bi-encoder retriever trained through contrastive learning and knowledge distillation. As the first trainable retrieval framework for UIE, RUIE serves as a universal plugin for various LLMs. Experimental results on eight held-out datasets demonstrate RUIE's effectiveness, with average F1-score improvements of 19.22 and 3.22 compared to instruction-tuning methods and other retrievers, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11673 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RUIE: Retrieval-based Unified Information Extraction using Large Language Model Liao, Xincheng Duan, Junwen Huang, Yixi Wang, Jianxin Computation and Language Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle to generalize to unseen tasks. We propose RUIE (Retrieval-based Unified Information Extraction), a framework that leverages in-context learning for efficient task generalization. RUIE introduces a novel demonstration selection mechanism combining LLM preferences with a keyword-enhanced reward model, and employs a bi-encoder retriever trained through contrastive learning and knowledge distillation. As the first trainable retrieval framework for UIE, RUIE serves as a universal plugin for various LLMs. Experimental results on eight held-out datasets demonstrate RUIE's effectiveness, with average F1-score improvements of 19.22 and 3.22 compared to instruction-tuning methods and other retrievers, respectively. |
| title | RUIE: Retrieval-based Unified Information Extraction using Large Language Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.11673 |