Tool Retrieval on ToolBench Standard queries G2 tier
73.6NDCG@5CoHyDE (r = 3)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoHyDE (r = 3)Expansion Factor (r)=32026.05 | 73.6 | 78 | |
| BGE (trained S1a)Backbone=BGE, Training Stage=S1a2026.05 | 71.7 | 76.3 | |
| HyDE (vanilla LLM + trained BGE S1a)Backbone=BGE (trained S1a), Query Expansion Strategy=HyDE, Generator=Qwen3.5-4B2026.05 | 59.5 | 62.2 | |
| text-embedding-3-largeBackbone=text-embedding-3-large2026.05 | 36.3 | 36.4 | |
| HyDE (vanilla LLM & BGE)Backbone=BGE (vanilla), Query Expansion Strategy=HyDE, Generator=Qwen3.5-4B2026.05 | 34.9 | 37.7 | |
| BGE (vanilla)Backbone=BGE, Training Stage=vanilla2026.05 | 31.9 | 33.2 | |
| BM252026.05 | 31 | 31.7 | |
| Query expansion (LLM + BGE)Backbone=BGE (vanilla), Query Expansion Strategy=Query-side paraphrasing2026.05 | 27 | 30 |