Update README.md

README.md

@@ -25,7 +25,7 @@ Inference Lab is an applied AI research and engineering organization. We develop
 
 A comprehensive data-centric study addressing the critical gaps in Roman Urdu NLP infrastructure. Covers rigorous dataset curation methodology, privacy-preserving embedding strategies, and systematic benchmarking of state-of-the-art models on Roman Urdu classification tasks. Establishes reproducible baselines for future work in this domain.
 
-→ [Preprint](https://doi.org/10.5281/zenodo.18080524)
+→ [Read here](https://doi.org/10.5281/zenodo.18080524)
 
 ---
 
@@ -33,10 +33,17 @@ A comprehensive data-centric study addressing the critical gaps in Roman Urdu NL
 
 Construction and release of the largest Roman Urdu emotion recognition corpus to date. Introduces a cross-institute annotation validation framework with structured annotator roles, multi-round calibration, and Inter-Annotator Agreement (IAA) measurement. Accompanies the current state-of-the-art emotion classifier for Roman Urdu.
 
-→ *Under Progress*
+→ [Read here](https://doi.org/10.21203/rs.3.rs-9759243/v1)
 
 ---
 
+**RUDaSA: Roman Urdu Dataset for Sentiment Analysis — A Large-Scale, Curated Corpus with Privacy-Preserving Embeddings and Competitive Benchmarking of Transformer Models**
+
+RUDaSA is a large-scale Roman Urdu sentiment analysis benchmark that provides privacy-preserving embeddings and evaluates state-of-the-art transformer models to advance NLP research for low-resource and code-mixed languages.
+
+→ [Read here](https://doi.org/10.21203/rs.3.rs-9827763/v1)
+
+
 ### Speech AI
 
 **Modeling Vocal Fatigue as Embedding-Space Deviation Using Contrastively Trained ECAPA-TDNNs**