# Knowledge Elicitation on ALCUNA Source: [Knowledge Elicitation on ALCUNA]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:05:02.442Z Evaluation of model performance on the ALCUNA dataset for Knowledge Elicitation tasks, measured by success rate. 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 | Knowledge Elicitation | | Dataset (including any stated split) | ALCUNA | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Discriminator | 3048 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 3048 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 210 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 210 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 90 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 90 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 80 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 80 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 72 | Not recorded | 68fa73681e209131cea5c4b3 | | Discriminator | 72 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 63 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 63 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 30 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 30 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 8 | Not recorded | 68fa73681e209131cea5c4b3 | | Few-shots | 8 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | PGDC | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | PGDC | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | PGDC | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | Zero-shot | 0 | Not recorded | 68fa73681e209131cea5c4b3 | | PGDC | 0 | Not recorded | 68fa73681e209131cea5c4b3 | ### Discriminator Success Rate: 3048. Result ID: 6992c8773a6c314849117ac3. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 3048. Result ID: 6992c8773a6c314849117ac6. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 210. Result ID: 6992c8773a6c314849117ad8. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 210. Result ID: 6992c8773a6c314849117adb. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 90. Result ID: 6992c8773a6c314849117aca. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 90. Result ID: 6992c8773a6c314849117acd. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 80. Result ID: 6992c8773a6c314849117ac9. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 80. Result ID: 6992c8773a6c314849117acc. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 72. Result ID: 6992c8773a6c314849117ad1. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Discriminator Success Rate: 72. Result ID: 6992c8773a6c314849117ad4. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 63. Result ID: 6992c8773a6c314849117ac2. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 63. Result ID: 6992c8773a6c314849117ac5. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 30. Result ID: 6992c8773a6c314849117ad7. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 30. Result ID: 6992c8773a6c314849117ada. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 8. Result ID: 6992c8773a6c314849117ad0. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Few-shots Success Rate: 8. Result ID: 6992c8773a6c314849117ad3. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117ac1. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117ac4. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### PGDC Success Rate: 0. Result ID: 6992c8773a6c314849117ac7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA2 (7B)"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117ac8. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117acb. [Reporting paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### PGDC Success Rate: 0. Result ID: 6992c8773a6c314849117ace. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Vicuna (7B)"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117acf. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117ad2. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### PGDC Success Rate: 0. Result ID: 6992c8773a6c314849117ad5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-J (6B)"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117ad6. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)","Prompt Variant":"standard"}. This record does not assert independent reproduction. ### Zero-shot Success Rate: 0. Result ID: 6992c8773a6c314849117ad9. [Reporting paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)","Prompt Variant":"paraphrased"}. This record does not assert independent reproduction. ### PGDC Success Rate: 0. Result ID: 6992c8773a6c314849117adc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-2 (774M)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.