Clinical Trial Matching on TREC 2022
76.5AccuracyαNeSy-CTM
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| αNeSy-CTMModel=gpt-oss-120b2026.06 | 76.5 | 64 | 89 | 76.1 | 54.7 | |
| NeSy-CTMModel=gpt-oss-120b2026.06 | 75 | 60 | 90 | 74.4 | 52.4 | |
| αNeSy-CTMModel=Average2026.06 | 73.7 | 57.3 | 90 | 73 | 50.1 | |
| CoTModel=gpt-oss-120b2026.06 | 73.5 | 88 | 59 | 72.9 | 49.1 | |
| Zero-shotModel=gpt-oss-120b2026.06 | 73 | 90 | 56 | 72.2 | 48.9 | |
| NeSy-CTMModel=qwen3-vl-32b-instruct2026.06 | 73 | 66 | 80 | 72.9 | 46.5 | |
| αNeSy-CTMModel=qwen3-vl-32b-instruct2026.06 | 73 | 60 | 86 | 72.5 | 47.6 | |
| NeSy-CTMModel=Average2026.06 | 72.7 | 59 | 86.3 | 72.2 | 47.1 | |
| αNeSy-CTMModel=olmo-3-32b-think2026.06 | 71.5 | 48 | 95 | 69.8 | 48.7 | |
| QuaSARModel=gpt-oss-120b2026.06 | 71 | 69 | 73 | 71 | 42 | |
| NeSy-CTMModel=olmo-3-32b-think2026.06 | 70 | 51 | 89 | 68.9 | 43.2 | |
| CoTModel=Average2026.06 | 68.8 | 81.9 | 55.5 | 68.2 | 38.9 | |
| CoTModel=qwen3-vl-32b-instruct2026.06 | 67 | 90 | 44 | 65.2 | 38.3 | |
| CoTModel=olmo-3-32b-think2026.06 | 65.8 | 67.7 | 63.9 | 65.8 | 31.6 | |
| QuaSARModel=Average2026.06 | 65.7 | 70 | 61.3 | 65.6 | 31.5 | |
| QuaSARModel=qwen3-vl-32b-instruct2026.06 | 65 | 66 | 64 | 65 | 30 | |
| Zero-shotModel=Average2026.06 | 65 | 88.7 | 41.3 | 62.9 | 34.1 | |
| Zero-shotModel=qwen3-vl-32b-instruct2026.06 | 61.5 | 94 | 29 | 57 | 30.3 | |
| QuaSARModel=olmo-3-32b-think2026.06 | 61 | 75 | 47 | 60.2 | 22.9 | |
| Zero-shotModel=olmo-3-32b-think2026.06 | 60.5 | 82 | 39 | 58.6 | 23.3 |