Information Retrieval on TravelDest
58.5NDCG@10BAGEL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| BAGELLLM Backbone=GPT-4o, Ranking Protocol=ER, LLM budget per query=502026.04 | 58.5 | 41.6 | 2.9 | 6.9 | |
| BAGELLLM Backbone=GPT-4o, Ranking Protocol=PR, LLM budget per query=502026.04 | 57 | 40.2 | 2.7 | 6.7 | |
| Pointwise LLMLLM Backbone=GPT-4o, Ranking Protocol=ER, LLM budget per query=502026.04 | 55.1 | 29.3 | 2.3 | 3.9 | |
| RankGPTLLM Backbone=GPT-4o, Ranking Method=Listwise, LLM budget per query=502026.04 | 53.3 | 28.8 | 2.3 | 3.9 | |
| BAGELLLM Backbone=Qwen3-14B, Ranking Protocol=ER, LLM budget per query=502026.04 | 51 | 38 | 2.5 | 6.8 | |
| BAGELLLM Backbone=Qwen3-14B, Ranking Protocol=PR, LLM budget per query=502026.04 | 49.8 | 37.4 | 2.5 | 6.7 | |
| Pointwise LLMLLM Backbone=GPT-4o, Ranking Protocol=PR, LLM budget per query=502026.04 | 48.9 | 28.2 | 2 | 3.9 | |
| RankGPTLLM Backbone=Baseline, Ranking Method=Listwise, LLM budget per query=502026.04 | 48.6 | 27.7 | 2.1 | 3.9 | |
| Pointwise LLMLLM Backbone=Qwen3-14B, Ranking Protocol=ER, LLM budget per query=502026.04 | 48.3 | 27.9 | 2.2 | 3.9 | |
| Pointwise LLMLLM Backbone=Qwen3-14B, Ranking Protocol=PR, LLM budget per query=502026.04 | 45.8 | 27.2 | 2.1 | 3.9 | |
| Cross EncoderLLM Backbone=Baseline, LLM budget per query=502026.04 | 43.1 | 26.4 | 1.7 | 3.9 | |
| Dense RetrieverLLM Backbone=Baseline, LLM budget per query=502026.04 | 22.3 | 21.6 | 0.9 | 3.9 | |
| BM25LLM Backbone=Baseline, LLM budget per query=502026.04 | 21.1 | 17.2 | 1 | 3.4 |