Reviewer Retrieval on LR-Bench Reviewer-Centric (test)
0.1783Expertise-aligned LossMERIT-Retriever-8B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MERIT-Retriever-8BMethod Category=Embedding-based Methods2026.05 | 0.1783 | 76.84 | |
| RATE-8BMethod Category=Embedding-based Methods2026.05 | 0.1857 | 75.63 | |
| SciNCLMethod Category=Embedding-based Methods2026.05 | 0.1938 | 75.03 | |
| CoFMethod Category=Embedding-based Methods2026.05 | 0.2175 | 73.34 | |
| SPECTER2 PRXMethod Category=Embedding-based Methods2026.05 | 0.2175 | 72.26 | |
| Qwen3-MaxMethod Category=LLM-based Methods, Decoding Strategy=greedy, Thinking Mode=enabled2026.05 | 0.2289 | 55.01 | |
| TPMSMethod Category=Statistical-based Methods2026.05 | 0.2322 | 72.01 | |
| DeepSeek-V3.2Method Category=LLM-based Methods, Decoding Strategy=greedy, Thinking Mode=enabled2026.05 | 0.2348 | 54.04 | |
| SPECTERMethod Category=Embedding-based Methods2026.05 | 0.2396 | 71.29 | |
| BERTScoreMethod Category=Embedding-based Methods2026.05 | 0.338 | 62.36 |