BM-K commited on
Commit
ef0015a
·
verified ·
1 Parent(s): c1b2e1d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
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