Spaces:
Running
Running
README: link the cited RAG assistant and its results
Browse files
README.md
CHANGED
|
@@ -24,4 +24,20 @@ right. A research demo, not a diagnostic tool.
|
|
| 24 |
Code, experiments and limitations: [github.com/marconcini/leafscan](https://github.com/marconcini/leafscan) ·
|
| 25 |
Model: [Marconcini/leafscan-convnext-tiny](https://huggingface.co/Marconcini/leafscan-convnext-tiny)
|
| 26 |
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
Code, experiments and limitations: [github.com/marconcini/leafscan](https://github.com/marconcini/leafscan) ·
|
| 25 |
Model: [Marconcini/leafscan-convnext-tiny](https://huggingface.co/Marconcini/leafscan-convnext-tiny)
|
| 26 |
|
| 27 |
+
## Beyond this page: a cited assistant (local only)
|
| 28 |
+
|
| 29 |
+
The full project adds a question-answering assistant after the diagnosis. It retrieves passages
|
| 30 |
+
from 28 Wikipedia articles, answers with a local LLM (Qwen3-4B) citing each source, says
|
| 31 |
+
"I don't know" when the sources do not answer, and flags with ⚠️ the sentences an NLI model
|
| 32 |
+
finds unsupported. Its models are ~10 GB, so it runs on your machine, not in this page:
|
| 33 |
+
|
| 34 |
+
```bash
|
| 35 |
+
pip install -e ".[app,rag]"
|
| 36 |
+
LEAFSCAN_ASSISTANT=1 python -m leafscan.app # photo → diagnosis → cited answers, Grad-CAM
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
What the evaluation showed: the assistant abstains on 86% of unanswerable test questions and
|
| 40 |
+
78% of its cited sentences are supported by their source; letting the diagnosis filter the
|
| 41 |
+
search would lose 16 points of recall, because a wrong diagnosis removes the answer. Details
|
| 42 |
+
in the [README](https://github.com/marconcini/leafscan#phase-2--rag-assistant) and the
|
| 43 |
+
[research log](https://github.com/marconcini/leafscan/blob/main/docs/research-log.md).
|