# Slot Filling and Intent Detection on PROSLU (test) Source: [Slot Filling and Intent Detection on PROSLU (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:25.577Z Evaluation of joint performance for Slot Filling and Intent Detection on the test split of the PROSLU dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Slot Filling and Intent Detection | | Dataset (including any stated split) | PROSLU (test) | | Metric | Slot F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Slot F1](): Higher is better; unit: PERCENT. - [Intent Accuracy](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Slot F1 | Result date | Report paper | | --- | --- | --- | --- | | ELECTRA | 84.38 | Not recorded | 68fa6b9c1e209131cea2f504 | | XLNet | 83.39 | Not recorded | 68fa6b9c1e209131cea2f504 | | General SLU Model | 83.27 | Not recorded | 68fa6b9c1e209131cea2f504 | | RoBERTa | 82.9 | Not recorded | 68fa6b9c1e209131cea2f504 | | BERT | 82.51 | Not recorded | 68fa6b9c1e209131cea2f504 | | Stack-Propagation | 81.08 | Not recorded | 68fa6b9c1e209131cea2f504 | | Bi-Model | 77.76 | Not recorded | 68fa6b9c1e209131cea2f504 | | Slot-Gated | 74.18 | Not recorded | 68fa6b9c1e209131cea2f504 | | SF-ID | 73.7 | Not recorded | 68fa6b9c1e209131cea2f504 | | XLNet | 46.92 | Not recorded | 68fa6b9c1e209131cea2f504 | | ELECTRA | 46.48 | Not recorded | 68fa6b9c1e209131cea2f504 | | RoBERTa | 45.92 | Not recorded | 68fa6b9c1e209131cea2f504 | | BERT | 44.8 | Not recorded | 68fa6b9c1e209131cea2f504 | | General SLU Model | 42.24 | Not recorded | 68fa6b9c1e209131cea2f504 | | SF-ID | 39.63 | Not recorded | 68fa6b9c1e209131cea2f504 | | Stack-Propagation | 39.29 | Not recorded | 68fa6b9c1e209131cea2f504 | | Bi-Model | 37.37 | Not recorded | 68fa6b9c1e209131cea2f504 | | Slot-Gated | 36.53 | Not recorded | 68fa6b9c1e209131cea2f504 | ### ELECTRA Slot F1: 84.38. Result ID: 698e99f5ffc3901de09f07bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### XLNet Slot F1: 83.39. Result ID: 698e99f5ffc3901de09f07b8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### General SLU Model Slot F1: 83.27. Result ID: 698e99f5ffc3901de09f07b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### RoBERTa Slot F1: 82.9. Result ID: 698e99f5ffc3901de09f07ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### BERT Slot F1: 82.51. Result ID: 698e99f5ffc3901de09f07b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### Stack-Propagation Slot F1: 81.08. Result ID: 698e99f5ffc3901de09f07b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### Bi-Model Slot F1: 77.76. Result ID: 698e99f5ffc3901de09f07ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### Slot-Gated Slot F1: 74.18. Result ID: 698e99f5ffc3901de09f07ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### SF-ID Slot F1: 73.7. Result ID: 698e99f5ffc3901de09f07b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/ Profile (using Multi-level Knowledge Adapter)"}. This record does not assert independent reproduction. ### XLNet Slot F1: 46.92. Result ID: 698e99f5ffc3901de09f07b7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### ELECTRA Slot F1: 46.48. Result ID: 698e99f5ffc3901de09f07bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### RoBERTa Slot F1: 45.92. Result ID: 698e99f5ffc3901de09f07b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### BERT Slot F1: 44.8. Result ID: 698e99f5ffc3901de09f07b5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Pre-trained-based","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### General SLU Model Slot F1: 42.24. Result ID: 698e99f5ffc3901de09f07b3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### SF-ID Slot F1: 39.63. Result ID: 698e99f5ffc3901de09f07af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### Stack-Propagation Slot F1: 39.29. Result ID: 698e99f5ffc3901de09f07b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### Bi-Model Slot F1: 37.37. Result ID: 698e99f5ffc3901de09f07ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/o Profile"}. This record does not assert independent reproduction. ### Slot-Gated Slot F1: 36.53. Result ID: 698e99f5ffc3901de09f07ab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Non Pre-trained","Profile":"w/o Profile"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.