Reviewer Retrieval on CMU Gold standard dataset
0.1842Expertise-aligned LossMERIT-Retriever-8B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MERIT-Retriever-8BMethod Category=Embedding-based Methods2026.05 | 0.1842 | 81.58 | |
| RATE-8BMethod Category=Embedding-based Methods2026.05 | 0.1991 | 80.09 | |
| DeepSeek-V3.2Method Category=LLM-based Methods, Decoding Strategy=greedy, Thinking Mode=enabled2026.05 | 0.2237 | 77.36 | |
| Qwen3-MaxMethod Category=LLM-based Methods, Decoding Strategy=greedy, Thinking Mode=enabled2026.05 | 0.2246 | 77.54 | |
| SPECTER2 PRXMethod Category=Embedding-based Methods2026.05 | 0.2436 | 75.64 | |
| CoFMethod Category=Embedding-based Methods2026.05 | 0.2564 | 74.36 | |
| SciNCLMethod Category=Embedding-based Methods2026.05 | 0.2663 | 73.37 | |
| TPMSMethod Category=Statistical-based Methods2026.05 | 0.2811 | 71.89 | |
| SPECTERMethod Category=Embedding-based Methods2026.05 | 0.2851 | 71.49 | |
| BERTScoreMethod Category=Embedding-based Methods2026.05 | 0.3414 | 65.86 |