Update README.md
Browse files
README.md
CHANGED
|
@@ -46,7 +46,8 @@ The table below presents the retrieval performance of several embedding models e
|
|
| 46 |
We report **Normalized Discounted Cumulative Gain (NDCG)** scores, which measure how well a ranked list of documents aligns with ground truth relevance. Higher values indicate better retrieval quality.
|
| 47 |
- **Avg. NDCG**: Average of NDCG@1, @3, @5, and @10 across all benchmark datasets.
|
| 48 |
- **NDCG@k**: Relevance quality of the top-*k* retrieved results.
|
| 49 |
-
|
|
|
|
| 50 |
#### 7 Datasets of MTEB (Korean)
|
| 51 |
Our model, **telepix/PIXIE-Rune-Preview**, achieves state-of-the-art performance across most metrics and benchmarks, demonstrating strong generalization across domains such as multi-hop QA, long-document retrieval, public health, and e-commerce.
|
| 52 |
|
|
|
|
| 46 |
We report **Normalized Discounted Cumulative Gain (NDCG)** scores, which measure how well a ranked list of documents aligns with ground truth relevance. Higher values indicate better retrieval quality.
|
| 47 |
- **Avg. NDCG**: Average of NDCG@1, @3, @5, and @10 across all benchmark datasets.
|
| 48 |
- **NDCG@k**: Relevance quality of the top-*k* retrieved results.
|
| 49 |
+
All evaluations were conducted using the open-source **[Korean-MTEB-Retrieval-Evaluators](https://github.com/BM-K/Korean-MTEB-Retrieval-Evaluators)** codebase to ensure consistent dataset handling, indexing, retrieval, and NDCG@k computation across models.
|
| 50 |
+
|
| 51 |
#### 7 Datasets of MTEB (Korean)
|
| 52 |
Our model, **telepix/PIXIE-Rune-Preview**, achieves state-of-the-art performance across most metrics and benchmarks, demonstrating strong generalization across domains such as multi-hop QA, long-document retrieval, public health, and e-commerce.
|
| 53 |
|