Clinical Trial Matching on TREC 2021
72AccuracyNeSy-CTM
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| NeSy-CTMModel=gpt-oss-120b2026.06 | 72 | 62 | 82 | 71.7 | 44.9 | |
| CoTModel=gpt-oss-120b2026.06 | 71.5 | 87 | 56 | 70.8 | 45.2 | |
| QuaSARModel=gpt-oss-120b2026.06 | 71.5 | 74 | 69 | 71.5 | 43.1 | |
| αNeSy-CTMModel=gpt-oss-120b2026.06 | 70.5 | 58 | 83 | 70 | 42.3 | |
| NeSy-CTMModel=olmo-3-32b-think2026.06 | 70.5 | 53 | 88 | 69.6 | 43.8 | |
| αNeSy-CTMModel=olmo-3-32b-think2026.06 | 70.3 | 53 | 87.9 | 69.5 | 43.6 | |
| NeSy-CTMModel=Average2026.06 | 70.3 | 60 | 80.7 | 70 | 41.6 | |
| αNeSy-CTMModel=Average2026.06 | 69.1 | 56.3 | 81.9 | 68.6 | 39.6 | |
| NeSy-CTMModel=qwen3-vl-32b-instruct2026.06 | 68.5 | 65 | 72 | 68.5 | 37.1 | |
| Zero-shotModel=gpt-oss-120b2026.06 | 68 | 85 | 51 | 67 | 38.3 | |
| αNeSy-CTMModel=qwen3-vl-32b-instruct2026.06 | 66.5 | 58 | 75 | 66.3 | 33.5 | |
| CoTModel=Average2026.06 | 66.3 | 79.7 | 52.8 | 65.7 | 33.8 | |
| QuaSARModel=qwen3-vl-32b-instruct2026.06 | 65.5 | 72 | 59 | 65.3 | 31.3 | |
| Zero-shotModel=olmo-3-32b-think2026.06 | 64.5 | 84 | 45 | 63.1 | 31.5 | |
| CoTModel=qwen3-vl-32b-instruct2026.06 | 64.5 | 84 | 45 | 63.1 | 31.5 | |
| Zero-shotModel=Average2026.06 | 64.5 | 86.7 | 42.3 | 62.7 | 32.4 | |
| QuaSARModel=Average2026.06 | 63.8 | 74.7 | 53 | 63.4 | 28.3 | |
| CoTModel=olmo-3-32b-think2026.06 | 62.8 | 68 | 57.6 | 62.7 | 25.7 | |
| Zero-shotModel=qwen3-vl-32b-instruct2026.06 | 61 | 91 | 31 | 57.1 | 27.5 | |
| QuaSARModel=olmo-3-32b-think2026.06 | 54.5 | 78 | 31 | 51.8 | 10.2 |