Krithika Ramesh
@stolenpyjak.bsky.social
(she/her)
¯\_(ツ)_/¯
PhD student @jhuclsp | Prev @IndiaMSR
¯\_(ツ)_/¯
PhD student @jhuclsp | Prev @IndiaMSR
Synthetic data shouldn’t be a black box - we make it easier to examine and identify issues in synthetic data outputs with
- Interactive text exploration & review with our GUI tool
- Exploring text diversity, structure and themes with our visual and descriptive text analyses tools
- Interactive text exploration & review with our GUI tool
- Exploring text diversity, structure and themes with our visual and descriptive text analyses tools
November 7, 2025 at 12:53 AM
Synthetic data shouldn’t be a black box - we make it easier to examine and identify issues in synthetic data outputs with
- Interactive text exploration & review with our GUI tool
- Exploring text diversity, structure and themes with our visual and descriptive text analyses tools
- Interactive text exploration & review with our GUI tool
- Exploring text diversity, structure and themes with our visual and descriptive text analyses tools
Conventional metrics like BLEU, ROUGE, or perplexity only scratch the surface of synthetic text quality!
Our framework introduces a multi-dimensional evaluation suite that covers aspects such as utility, privacy, fairness and distributional similarity to the real data.
Our framework introduces a multi-dimensional evaluation suite that covers aspects such as utility, privacy, fairness and distributional similarity to the real data.
November 7, 2025 at 12:53 AM
Conventional metrics like BLEU, ROUGE, or perplexity only scratch the surface of synthetic text quality!
Our framework introduces a multi-dimensional evaluation suite that covers aspects such as utility, privacy, fairness and distributional similarity to the real data.
Our framework introduces a multi-dimensional evaluation suite that covers aspects such as utility, privacy, fairness and distributional similarity to the real data.