|
--- |
|
license: mit |
|
language: |
|
- en |
|
pipeline_tag: question-answering |
|
--- |
|
This model is a 7B model with credibility-aware generation, capable of understanding and leveraging credibility in context for generation, thus being robust to noisy documents. Because of the capability of customized credibility in CAG, it has diverse application scenarios, including personalized response generation and the resolution of knowledge conflicts. |
|
|
|
Read our [article](https://arxiv.org/abs/2404.06809) to learn more. |
|
|
|
Evaluate our model in real scenarios including Open-domain QA, Time-sensitive QA, and Misinformation Polluted QA. For more information and to access the evaluation code, visit [Code](https://github.com/panruotong/CAG). |
