Add pipeline tag and Hugging Face paper link

This PR improves the model card by:

- Adding the `pipeline_tag: text-retrieval` to the metadata, which ensures the model can be discovered via the Hugging Face Hub's pipeline filters (e.g., at https://huggingface.co/models?pipeline_tag=text-retrieval). This accurately reflects the model's function as a dense retriever.
- Adding a prominent link to the official Hugging Face paper page (`https://huggingface.co/papers/2507.03922`) at the top of the model card for easy access.
- Clarifying the existing paper references in the `Introduction` and `Model List` sections to explicitly mention "on arXiv" without replacing the original arXiv links.

The existing sample usage, GitHub link, and license information are preserved as they are already correctly provided.

README.md

@@ -1,20 +1,22 @@
 ---
-tags:
-- transformers
-- sentence-transformers
+base_model:
+- bge-large-en-v1.5
 language:
 - en
-license: apache-2.0
 library_name: transformers
-base_model:
-- bge-large-en-v1.5
+license: apache-2.0
+pipeline_tag: text-retrieval
+tags:
+- transformers
+- sentence-transformers
 model_index:
 - name: kpr-bge-large-en-v1.5
-results:
 ---
 
 # Knowledgeable Embedding: kpr-bge-large-en-v1.5
 
+This model is presented in the paper [Dynamic Injection of Entity Knowledge into Dense Retrievers](https://huggingface.co/papers/2507.03922).
+
 ## Introduction
 
 **Injecting dynamically updatable entity knowledge into embeddings to enhance RAG**
@@ -27,7 +29,7 @@ Although RAG typically relies on embedding-based retrieval, the embedding models
 
 **The entity knowledge is pluggable and can be dynamically updated.**
 
-For further details, refer to [our paper](https://arxiv.org/abs/2507.03922) or [GitHub repository](https://github.com/knowledgeable-embedding/knowledgeable-embedding).
+For further details, refer to [our paper on arXiv](https://arxiv.org/abs/2507.03922) or [GitHub repository](https://github.com/knowledgeable-embedding/knowledgeable-embedding).
 
 ## Model List
 
@@ -39,7 +41,7 @@ For further details, refer to [our paper](https://arxiv.org/abs/2507.03922) or [
 | [knowledgeable-ai/kpr-bge-base-en-v1.5](https://huggingface.co/knowledgeable-ai/kpr-bge-base-en-v1.5) | 112M | [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) |
 | [knowledgeable-ai/kpr-bge-large-en-v1.5](https://huggingface.co/knowledgeable-ai/kpr-bge-large-en-v1.5) | 340M | [bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) |
 
-For practical use, we recommend `knowledgeable-ai/kpr-bge-*`, which significantly outperforms state-of-the-art models on queries involving less-frequent entities while performing comparably on other queries, as reported in [our paper](https://arxiv.org/abs/2507.03922).
+For practical use, we recommend `knowledgeable-ai/kpr-bge-*`, which significantly outperforms state-of-the-art models on queries involving less-frequent entities while performing comparably on other queries, as reported in [our paper on arXiv](https://arxiv.org/abs/2507.03922).
 
 Regarding the model size, we do not count the entity embeddings since they are stored in CPU memory and have a negligible impact on runtime performance. See [this page](https://github.com/knowledgeable-embedding/knowledgeable-embedding/wiki/Internals-of-Knowledgeable-Embedding) for details.