Update README.md

README.md

@@ -29,7 +29,7 @@ model-index:
 
 <h1 align="center">roberta-incoherence-classifier</h1>
 
-Encoder-based classifier for document inconsistency detection in **Polish**. This model evaluates the semantic consistency between two text fragments (e.g. sections of legal, procurement or organizational documents). It follows an NLI-like setup but **redefines labels specifically for document coherence auditing**.
+Encoder-based classifier for document inconsistency detection in **Polish**. This model evaluates the semantic consistency between two text fragments (e.g. sections of legal, procurement or organizational documents). It follows an NLI-like setup but **redefines labels specifically for document coherence auditing**. This model was **initalized from [PKOBP/polish-roberta-8k](https://huggingface.co/PKOBP/polish-roberta-8k)** and **adapted into an inconsistency classifier** through supervised training on high-quality document-style pairs.
 
 ---
 
@@ -96,7 +96,7 @@ Finetuning on specific domain data is recommended for best production accuracy.
 
 ---
 
-## Evaluation (internal benchmark, n=450)
+## Evaluation (on [asseco-group/incoherence-bench](https://huggingface.co/datasets/asseco-group/incoherence-bench), test split)
 
 ```
                precision    recall  f1-score   support