Semantic Role Labeling on CoNLL English Brown 2009 (test)
86.05F1 ScoreLlama3-8B (Fine-tune)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Llama3-8B (Fine-tune)Predicates=With pre-identified, Model Type=Fine-tuned LLM2025.06 | 86.05 | 88.41 | 84.21 | |
| Li et al. (2020) + BERTPredicates=With pre-identified, Backbone=BERT2025.06 | 85.13 | 86.49 | 83.8 | |
| Fernández-González (2023) + BERTPredicates=With pre-identified, Backbone=BERT2025.06 | 84.4 | 84.5 | 84.2 | |
| UniSRLModel Type=Single, Predicate Setting=Pre-identified2019.01 | 81.5 | 81.7 | 81.4 | |
| Zhou et al. (2020) + BERTPredicates=With pre-identified, Backbone=BERT2025.06 | 81.43 | 81.89 | 80.98 | |
| Llama3-8B (Fine-tune)Predicates=Without pre-identified, Model Type=Fine-tuned LLM2025.06 | 81.14 | 83.36 | 79.04 | |
| Li et al. (2020)Predicates=With pre-identified2025.06 | 80.63 | 82.6 | 78.75 | |
| Fernández-González (2023)Predicates=With pre-identified2025.06 | 80.6 | 80.6 | 80.5 | |
| Fernández-González (2023) + BERTPredicates=Without pre-identified, Backbone=BERT2025.06 | 80.4 | 79.9 | 81.8 | |
| Zhou et al. (2020) + BERTPredicates=Without pre-identified, Backbone=BERT2025.06 | 80.34 | 79.06 | 81.67 | |
| Li et al. (2020) + BERTPredicates=Without pre-identified, Backbone=BERT2025.06 | 79.9 | 80.01 | 79.8 | |
| Li et al. (2018b)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 79.8 | 80.6 | 79 | |
| He et al. (2018b)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 79.3 | 81.9 | 76.9 | |
| Cai et al. (2018)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 79 | 79.8 | 78.3 | |
| Marcheggiani and Titov (2017)Model Type=Ensemble, Predicate Setting=Pre-identified2019.01 | 78.9 | 80.8 | 77.1 | |
| Marcheggiani et al. (2017)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 77.7 | 79.4 | 76.2 | |
| Zhou et al. (2020)Predicates=Without pre-identified2025.06 | 77.47 | 76.46 | 78.52 | |
| Marcheggiani and Titov (2017)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 77.2 | 78.5 | 75.9 | |
| Roth and Lapata (2016)Model Type=Ensemble, Predicate Setting=Pre-identified2019.01 | 76.5 | 79.7 | 73.6 | |
| Roth and Lapata (2016) (Global)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 76.1 | 78.6 | 73.8 | |
| Zhou et al. (2020)Predicates=With pre-identified2025.06 | 75.72 | 76.92 | 74.55 | |
| FitzGerald et al. (2015)Model Type=Ensemble, Predicate Setting=Pre-identified2019.01 | 75.5 | — | — | |
| Fernández-González (2023)Predicates=Without pre-identified2025.06 | 75.4 | 74.4 | 76.4 | |
| FitzGerald et al. (2015) (Struct.)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 75.2 | — | — | |
| Zhao et al. (2009)Model Type=Single, Predicate Setting=Pre-identified2019.01 | 74.6 | — | — | |
| Li et al. (2020)Predicates=Without pre-identified2025.06 | 73.9 | 74.65 | 73.17 | |
| Llama3-8B (Frozen)Predicates=With pre-identified, Model Type=Frozen LLM2025.06 | 5.58 | 4.7 | 6.87 | |
| Llama3-8B (Frozen)Predicates=Without pre-identified, Model Type=Frozen LLM2025.06 | 3.01 | 3.14 | 2.89 |