|
--- |
|
datasets: |
|
- cognitivecomputations/dolphin |
|
- cognitivecomputations/dolphin-coder |
|
- Open-Orca/OpenOrca |
|
language: |
|
- en |
|
library_name: transformers |
|
tags: |
|
- legal |
|
--- |
|
# Redactable-LLM |
|
The high-level overview for integrating multiple Open Source Large Language Models within the AutoGen Framework is as follows: |
|
|
|
### Development of Custom Agents |
|
- **Agent Design**: Tasks include NLP/NER/PII identification, interpreting natural language commands, executing document redaction, and final verification. |
|
- **Customization**: Custom agents trained on specific tasks related to each aspect of the redaction process. |
|
- **Human Interaction**: Implement features to facilitate seamless human-agent interaction, allowing users to input commands and queries naturally (Optional) |
|
|
|
### LLM & VLLM AutoGen Integration |
|
|
|
- **Model Selection**: Automatic, task-dependent agent selection. |
|
- **Enhanced Inference**: Enhanced LLM inference features for optimal performance, including tuning, caching, error handling, and templating. |
|
- **Quality Control**: Vision agents analyze redacted documents using Set-of-Mark (SoM) prompting. Rejected documents are reprocessed and reviewed. |
|
- |
|
 |
|
|
|
### System Optimization |
|
- **Workflow Automation**: Automate the redaction workflow using a blend of LLMs, custom agents, and human inputs for efficient detection and redaction of sensitive information. |
|
- **Performance Maximization**: Optimize the system for both efficiency and accuracy, utilizing AutoGen's complex workflow management features. |
|
|
|
### User Interface Development |
|
- **Interface Design**: Develop a user-friendly interface that enables non-technical users to interact with the system via natural language prompts. |
|
- **Feedback Integration**: Implement a feedback loop to continuously refine the system's accuracy and user-friendliness based on user inputs. |
|
- **User Knowledgebase**: (Optional) User account, profile, and domain knowledge will be accessible by the `Research` agent, for personalized interaction and results. |
|
|
|
### Training, Testing and Validation |
|
- **Model Training**: Develop new datasets, focused on document understanding related to redaction. |
|
- **Unit Testing**: Conduct extensive unit tests to ensure individual system components function correctly. |
|
- **System Testing**: Perform comprehensive end-to-end testing to validate the entire redaction process, from user input to output. |
|
- **User Trials**: Facilitate user trials to gather feedback and make necessary system adjustments. |
|
--- |
|
|
|
- #### Mistral AI (LLM) |
|
[Paper](https://mistral.ai/news/mixtral-of-experts/) | [Model](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) |
|
|
|
- #### QwenLM (VLLM) |
|
[Paper](https://arxiv.org/abs/2308.12966) | [Code](https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file) | [Paper: Set-of-Mark Prompting](https://arxiv.org/abs/2310.11441) |
|
|
|
- #### AutoGen |
|
[Paper](https://arxiv.org/abs/2308.08155) | [Code](https://github.com/microsoft/autogen/tree/main) |
|
|
|
- #### Gretel AI (Synthetic Dataset Generation) |
|
[Model Page](https://gretel.ai/solutions/public-sector) | [Code](https://github.com/gretelai) | [Paper: Textbooks Are All You Need II](https://arxiv.org/abs/2309.05463) |
