npip99 commited on
Commit
9ae8623
·
1 Parent(s): b269504

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -1
README.md CHANGED
@@ -45,4 +45,21 @@ scores = model.predict(query_documents)
45
  print(scores)
46
  ```
47
 
48
- The model can also be inferenced using ZeroEntropy's [/models/rerank](https://docs.zeroentropy.dev/api-reference/models/rerank) endpoint.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  print(scores)
46
  ```
47
 
48
+ The model can also be inferenced using ZeroEntropy's [/models/rerank](https://docs.zeroentropy.dev/api-reference/models/rerank) endpoint, and on [AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-o7avk66msiukc).
49
+
50
+ ## Evaluations
51
+
52
+ NDCG@10 scores between `zerank-2` and competing closed-source proprietary rerankers. Since we are evaluating rerankers, OpenAI's `text-embedding-3-small` is used as an initial retriever for the Top 100 candidate documents.
53
+
54
+ | Domain | OpenAI embeddings | ZeroEntropy zerank-2 | ZeroEntropy zerank-1 | Gemini 2.5 Flash (Listwise) | Cohere rerank-3.5 |
55
+ |------------------|-------------------|----------------------|----------------------|-----------------------------|-------------------|
56
+ | Web | 0.3819 | **0.6346** | 0.6069 | 0.5765 | 0.5594 |
57
+ | Conversational | 0.4305 | **0.6140** | 0.5801 | 0.6021 | 0.5648 |
58
+ | STEM & Logic | 0.3744 | **0.6521** | 0.6283 | 0.5447 | 0.5418 |
59
+ | Code | 0.4582 | **0.6528** | 0.6310 | 0.6128 | 0.5364 |
60
+ | Legal | 0.4101 | **0.6644** | 0.6222 | 0.5565 | 0.5257 |
61
+ | Biomedical | 0.4783 | **0.7217** | 0.6967 | 0.5371 | 0.6246 |
62
+ | Finance | 0.6232 | 0.7600 | 0.7539 | **0.7694** | 0.7402 |
63
+ | **Average** | **0.4509** | **0.6714** | **0.6456** | **0.5999** | **0.5847** |
64
+
65
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/65ec60ccfc59f6e77ecc9ccb/UiDp8LsY4XIdRK5i3CAdD.png" alt="Graph showing the same table" width="1000"/>