Spaces:

gsarti
/

pecore

Running on Zero

gsarti commited on Oct 28

Commit

6d7e07c

•

1 Parent(s): 44f7b3c

Update contents.py

Files changed (1) hide show

contents.py CHANGED Viewed

@@ -7,7 +7,9 @@ PECoRe is a framework for trustworthy language generation using only model inter
 generations to its available input context. Given a query-context input pair, PECoRe identifies which tokens in the generated
 response were more dependant on context (<span class="category-label" style="background-color:#5fb77d; color: black; font-weight: var(--weight-semibold)">Context sensitive </span>), and match them with context tokens contributing the most to their prediction (<span class="category-label" style="background-color:#80ace8; color: black; font-weight: var(--weight-semibold)">Influential context </span>).
-Check out <a href="https://openreview.net/forum?id=XTHfNGI3zT" target='_blank'>our ICLR 2024 paper</a> for more details. A new paper applying PECoRe to retrieval-augmented QA is forthcoming ✨ stay tuned!
 """
 how_it_works_intro = """

 generations to its available input context. Given a query-context input pair, PECoRe identifies which tokens in the generated
 response were more dependant on context (<span class="category-label" style="background-color:#5fb77d; color: black; font-weight: var(--weight-semibold)">Context sensitive </span>), and match them with context tokens contributing the most to their prediction (<span class="category-label" style="background-color:#80ace8; color: black; font-weight: var(--weight-semibold)">Influential context </span>).
+Check out <a href="https://openreview.net/forum?id=XTHfNGI3zT" target='_blank'>our ICLR 2024 paper</a> for more details.
+✨ NEW: Check out <a href="https://arxiv.org/abs/2406.13663" target='_blank'>MIRAGE</a>, our PECoRe-based method for interpretability-based LLM citations! (demo <a href="https://huggingface.co/spaces/gsarti/mirage" target='_blank'>here</a>)
 """
 how_it_works_intro = """