# Binary deficiency detection on gold-labeled ICLR (test) Source: [Binary deficiency detection on gold-labeled ICLR (test)]() Collection index: [llms.txt]() Data updated: 2026-05-27T09:41:42.506Z Evaluation of binary deficiency detection performance on the test split of the gold-labeled ICLR dataset, reporting Accuracy, Precision, Recall, and F1 scores. 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 | Binary deficiency detection | | Dataset (including any stated split) | gold-labeled ICLR (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | TADDLE (Qwen3-30B-A3B + 9B integrator) | 86 | Not recorded | 6a167ac4dbd7150506f8016f | | Longformer-base-4096 | 83.33 | Not recorded | 6a167ac4dbd7150506f8016f | | BERT-base-uncased | 77.33 | Not recorded | 6a167ac4dbd7150506f8016f | | RottenReviews (LR) | 68 | Not recorded | 6a167ac4dbd7150506f8016f | | ReviewGuard (Llama-3.1-8B) | 66 | Not recorded | 6a167ac4dbd7150506f8016f | | RottenReviews (Llama-3-8B FT) | 65.33 | Not recorded | 6a167ac4dbd7150506f8016f | | ReviewGuard (Qwen3-8B) | 63.33 | Not recorded | 6a167ac4dbd7150506f8016f | | GLM 4.7 | 61.56 | Not recorded | 6a167ac4dbd7150506f8016f | | RottenReviews (XGBoost) | 60.22 | Not recorded | 6a167ac4dbd7150506f8016f | | RottenReviews (Random Forest) | 58.89 | Not recorded | 6a167ac4dbd7150506f8016f | | Qwen3.5-Plus | 55.33 | Not recorded | 6a167ac4dbd7150506f8016f | | Qwen3-30B | 54.44 | Not recorded | 6a167ac4dbd7150506f8016f | | DeepSeek V3.2 | 49.78 | Not recorded | 6a167ac4dbd7150506f8016f | | BigBird-RoBERTa-base | 46 | Not recorded | 6a167ac4dbd7150506f8016f | | RottenReviews (MLP) | 31.11 | Not recorded | 6a167ac4dbd7150506f8016f | | RottenReviews (Qwen3-8B 0-shot) | 31.11 | Not recorded | 6a167ac4dbd7150506f8016f | ### TADDLE (Qwen3-30B-A3B + 9B integrator) Accuracy: 86. Result ID: 6a16bc43fbc373592c104a7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Family":"Ours","Backbone":"Qwen3-30B-A3B","Integrator":"9B"}. This record does not assert independent reproduction. ### Longformer-base-4096 Accuracy: 83.33. Result ID: 6a16bc43fbc373592c104a72. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Family":"PLM"}. This record does not assert independent reproduction. ### BERT-base-uncased Accuracy: 77.33. Result ID: 6a16bc43fbc373592c104a70. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Family":"PLM"}. This record does not assert independent reproduction. ### RottenReviews (LR) Accuracy: 68. Result ID: 6a16bc43fbc373592c104a79. [Reporting paper]() Recorded evaluation configuration: {"Family":"Review-quality detector"}. This record does not assert independent reproduction. ### ReviewGuard (Llama-3.1-8B) Accuracy: 66. Result ID: 6a16bc43fbc373592c104a77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Family":"Review-quality detector"}. This record does not assert independent reproduction. ### RottenReviews (Llama-3-8B FT) Accuracy: 65.33. Result ID: 6a16bc43fbc373592c104a7e. [Reporting paper]() Recorded evaluation configuration: {"Family":"Review-quality detector","Fine-tuned":"true"}. This record does not assert independent reproduction. ### ReviewGuard (Qwen3-8B) Accuracy: 63.33. Result ID: 6a16bc43fbc373592c104a78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Family":"Review-quality detector"}. This record does not assert independent reproduction. ### GLM 4.7 Accuracy: 61.56. Result ID: 6a16bc43fbc373592c104a76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Family":"Few-shot LLM"}. This record does not assert independent reproduction. ### RottenReviews (XGBoost) Accuracy: 60.22. Result ID: 6a16bc43fbc373592c104a7c. [Reporting paper]() Recorded evaluation configuration: {"Family":"Review-quality detector"}. This record does not assert independent reproduction. ### RottenReviews (Random Forest) Accuracy: 58.89. Result ID: 6a16bc43fbc373592c104a7a. [Reporting paper]() Recorded evaluation configuration: {"Family":"Review-quality detector"}. This record does not assert independent reproduction. ### Qwen3.5-Plus Accuracy: 55.33. Result ID: 6a16bc43fbc373592c104a74. [Reporting paper]() Recorded evaluation configuration: {"Family":"Few-shot LLM"}. This record does not assert independent reproduction. ### Qwen3-30B Accuracy: 54.44. Result ID: 6a16bc43fbc373592c104a75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Family":"Few-shot LLM"}. This record does not assert independent reproduction. ### DeepSeek V3.2 Accuracy: 49.78. Result ID: 6a16bc43fbc373592c104a73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Family":"Few-shot LLM"}. This record does not assert independent reproduction. ### BigBird-RoBERTa-base Accuracy: 46. Result ID: 6a16bc43fbc373592c104a71. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Family":"PLM"}. This record does not assert independent reproduction. ### RottenReviews (MLP) Accuracy: 31.11. Result ID: 6a16bc43fbc373592c104a7b. [Reporting paper]() Recorded evaluation configuration: {"Family":"Review-quality detector"}. This record does not assert independent reproduction. ### RottenReviews (Qwen3-8B 0-shot) Accuracy: 31.11. Result ID: 6a16bc43fbc373592c104a7d. [Reporting paper]() Recorded evaluation configuration: {"Family":"Review-quality detector","Shot-count":"0-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.