|
--- |
|
license: llama2 |
|
datasets: |
|
- ACE05 |
|
- conll2003 |
|
- conll2012_ontonotesv5 |
|
- rams |
|
- tacred |
|
- fewrel |
|
- maven |
|
language: |
|
- en |
|
metrics: |
|
- f1 |
|
pipeline_tag: text-generation |
|
tags: |
|
- text-generation-inference |
|
- Information Extraction |
|
- IE |
|
- Named Entity Recogniton |
|
- Event Extraction |
|
- Relation Extraction |
|
- LLaMA |
|
--- |
|
|
|
# Model Card for ADELIE-SFT-3B |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
<p align="justify"> |
|
We introduce <b>ADELIE</b> (<b>A</b>ligning large language mo<b>DEL</b>s on <b>I</b>nformation <b>E</b>xtraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus <font face="Verdana">IEInstruct</font> for IE. Then we train ADELIE<sub>SFT</sub> using instruction tuning on <font face="Verdana">IEInstruct</font>. We further train ADELIE<sub>SFT</sub> with direct preference optimization (DPO) objective, resulting in ADELIE<sub>DPO</sub>. Extensive experiments on various held-out IE datasets demonstrate that our models (ADELIE<sub>SFT</sub> and ADELIE<sub>DPO</sub>) achieve state-of-the-art (SoTA) performance among open-source models. We further explore the general capabilities of ADELIE, and experimental results reveal that their general capabilities do not exhibit a noticeable decline. |
|
|
|
- 📖 Paper: [ADELIE: Aligning Large Language Models on Information Extraction](https://arxiv.org/abs/2405.05008) |
|
</p> |
|
- 🐧 Github: [THU/ADELIE](https://github.com/THU-KEG/ADELIE/tree/main) |
|
|
|
|
|
# Model Performance |
|
|
|
The table below presents the average F1 scores (%) of the ADELIE model across closed IE, open IE, and on-demand IE tasks, as well as its overall performance (%) on general benchmarks. For dataset details, please refer to the paper. |
|
|
|
| Model | Closed IE | Open IE | On-demand IE | General Average Score | |
|
|-----------------|-----------|---------|--------------|-----------------------| |
|
| Llama2 7B | 5.7 | 5.6 | 22.4 | 52.2 | |
|
| ADELIE-SFT | 42.6 | 46.9 | 60.4 | 53.5 | |
|
| ADELIE-DPO | **42.7** | **47.6** | **60.5** | **53.8** | |
|
|-----------------|-----------|---------|--------------|-----------------------| |
|
| Llama3.2 3B | 19.1 | 18.5 | 20.8 | 55.5 | |
|
| ADELIE-SFT-3B | **41.8** | 47.6 | **60.8** | **55.6** | |
|
| ADELIE-DPO-3B | 39.2 | **47.8** | 60.7 | **55.6** | |
|
|-----------------|-----------|---------|--------------|-----------------------| |
|
| Qwen2.5 1.5B | 16.5 | 14.2 | 20.5 | 54.6 | |
|
| ADELIE-SFT-1.5B | 37.7 | 44.6 | 58.9 | 55.0 | |
|
| ADELIE-DPO-1.5B | **38.5** | **45.6** | **59.2** | **55.1** | |
|
|
|
|
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
|
|
|
|
- **Developed by:** Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li |
|
- **Model type:** Text Generation |
|
- **Language(s) (NLP):** English |
|
- **License:** LLaMA2 License for the base model. |
|
- **Finetuned from model [optional]:** LLaMA3.2-3B |
|
|
|
|
