Argument Role Extraction on M2E2 text-only
75PrecisionFSMEE
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| FSMEE2026.02 | 75 | 2.6 | 5.1 | — | |
| KE-MME2026.02 | 51.9 | 37.5 | 39.3 | — | |
| RMPL (Mc)Backbone=Qwen3-VL-8B2026.02 | 50.6 | 57.6 | 53.9 | — | |
| RMPL (Ma)Backbone=Qwen2-VL-7B2026.02 | 48.9 | 59.1 | 53.5 | — | |
| RMPL (Mb)Backbone=InternVL3_5-8B2026.02 | 48.9 | 58.4 | 53.2 | — | |
| X-MTL2026.02 | 34.6 | 37.6 | 36 | — | |
| X-MTL2026.03 | 34.6 | 37.6 | 36 | — | |
| MMUTF2026.02 | 33.6 | 44.2 | 38.2 | — | |
| MMUTF2026.03 | 33.6 | 44.2 | 38.2 | — | |
| ECHOBackbone=Qwen3-14B2026.03 | 33.6 | 53.1 | 41.1 | — | |
| ECHOBackbone=Qwen3-32B2026.03 | 32.7 | 56.2 | 41.4 | — | |
| ECHOBackbone=DeepSeek-V3.22026.03 | 32.3 | 57.2 | 41.3 | — | |
| ECHOBackbone=Qwen3-8B2026.03 | 32.2 | 53.8 | 40.3 | — | |
| MMUTFEvaluation Protocol=ORIGINAL2026.06 | 31.5 | 46.8 | 37.7 | — | |
| X-MTLEvaluation Protocol=ORIGINAL2026.06 | 29.9 | 38.9 | 33.8 | — | |
| MGIM2026.02 | 28.2 | 34.7 | 31.2 | — | |
| UniCL2026.02 | 27.8 | 34.3 | 30.7 | — | |
| UniCL2026.03 | 27.8 | 34.3 | 30.7 | — | |
| WASE_att2026.02 | 27.5 | 33.2 | 30.1 | — | |
| WASE-att2026.03 | 27.5 | 33.2 | 30.1 | — | |
| ECHOBackbone=GPT-52026.03 | 27.2 | 62.3 | 37.9 | — | |
| CAMEL2026.02 | 24.8 | 41.8 | 31.1 | — | |
| CAMEL2026.03 | 24.8 | 41.8 | 31.1 | — | |
| WASE_obj2026.02 | 23.5 | 30.3 | 26.4 | — | |
| WASE-obj2026.03 | 23.5 | 30.3 | 26.4 | — | |
| CAMELEvaluation Protocol=ORIGINAL2026.06 | 23.5 | 41.8 | 30.1 | — | |
| WASE-T2026.03 | 21.4 | 30.1 | 24.9 | — | |
| X-MTLEvaluation Protocol=STRICTEVAL2026.06 | 20.2 | 41.7 | 27.2 | -6.6 | |
| FLAT2026.02 | 20.1 | 27.1 | 23.1 | — | |
| Flat2026.03 | 20.1 | 27.1 | 23.1 | — | |
| CAMELEvaluation Protocol=STRICTEVAL2026.06 | 16.1 | 36.1 | 22.3 | -7.8 | |
| MMUTFEvaluation Protocol=STRICTEVAL2026.06 | 15.9 | 51.7 | 24.3 | -13.4 | |
| SINGLE TASKEvaluation Protocol=STRICTEVAL2026.06 | 14.2 | 48.4 | 21.9 | — |