pyr0ball
3765fbc0f9
three-layer approach to stop 7B model from supplementing retrieved context
with training-data knowledge:
1. system prompt redesigned: 'no memory of books/stories/authors' eliminates
the model's self-permission to draw on parametric knowledge
2. quote-first prompt structure: model must commit to a specific quoted passage
before generating an answer — explicit NOT FOUND required when excerpts lack
the answer, preventing the 'excerpt doesn't say X... however in the series...'
escape pattern
3. _strip_escape() post-processor: catches any residual leakage by scanning for
known escape phrases ('in the series', 'by terry goodkind', 'it can be assumed',
etc.) and replacing the response with the canned no-answer message
|
||
|---|---|---|
| .. | ||
| api | ||
| services | ||
| __init__.py | ||
| config.py | ||
| deps.py | ||
| main.py | ||