| title: MIRAGE | |
| emoji: 🌴 | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 4.44.0 | |
| app_file: app.py | |
| pinned: true | |
| license: apache-2.0 | |
| short_description: Model Internals to generate RAG citations | |
| tags: | |
| - answer-attribution | |
| - interpretability | |
| - context-usage | |
| - language-modeling | |
| - arxiv:2406.13663 | |
| - arxiv:2402.05602 | |
| Demo for the paper [Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation](https://arxiv.org/abs/2406.13663) using the AttnLRP method from [AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers](https://arxiv.org/abs/2402.05602). |