# LLM Text Attribution on WritingPrompts Source: [LLM Text Attribution on WritingPrompts]() Collection index: [llms.txt]() Data updated: 2026-03-24T14:25:15.073Z Evaluation of a model's ability to attribute generated text to its source model using the WritingPrompts dataset, typically measured using metrics derived from detection curves like True Positive Rate at a fixed False Positive 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 | LLM Text Attribution | | Dataset (including any stated split) | WritingPrompts | | Metric | TPR (FPR=0.01) | | 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 - [TPR (FPR=0.01)](): Higher is better; unit: PERCENT. ## Recorded results | Method | TPR (FPR=0.01) | Result date | Report paper | | --- | --- | --- | --- | | log p(x) | 100 | Not recorded | 68fa5d701e209131ce9da3ce | | LogRank | 100 | Not recorded | 68fa5d701e209131ce9da3ce | | log p(x) | 100 | Not recorded | 68fa5d701e209131ce9da3ce | | LogRank | 100 | Not recorded | 68fa5d701e209131ce9da3ce | | Ours | 100 | Not recorded | 68fa5d701e209131ce9da3ce | | Binoculars | 99 | Not recorded | 68fa5d701e209131ce9da3ce | | Ours | 99 | Not recorded | 68fa5d701e209131ce9da3ce | | Binoculars | 99 | Not recorded | 68fa5d701e209131ce9da3ce | | Binoculars | 97 | Not recorded | 68fa5d701e209131ce9da3ce | | Ours | 90 | Not recorded | 68fa5d701e209131ce9da3ce | | LogRank | 54 | Not recorded | 68fa5d701e209131ce9da3ce | | Rank | 49 | Not recorded | 68fa5d701e209131ce9da3ce | | log p(x) | 46 | Not recorded | 68fa5d701e209131ce9da3ce | | Rank | 43 | Not recorded | 68fa5d701e209131ce9da3ce | | Rank | 39 | Not recorded | 68fa5d701e209131ce9da3ce | | Entropy | 0 | Not recorded | 68fa5d701e209131ce9da3ce | | Entropy | 0 | Not recorded | 68fa5d701e209131ce9da3ce | | Entropy | 0 | Not recorded | 68fa5d701e209131ce9da3ce | ### log p(x) TPR (FPR=0.01): 100. Result ID: 69c29e6047f34ce924ab3f31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"LLAMA 3 8B"}. This record does not assert independent reproduction. ### LogRank TPR (FPR=0.01): 100. Result ID: 69c29e6047f34ce924ab3f33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"LLAMA 3 8B"}. This record does not assert independent reproduction. ### log p(x) TPR (FPR=0.01): 100. Result ID: 69c29e6047f34ce924ab3f3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"QWEN 32B"}. This record does not assert independent reproduction. ### LogRank TPR (FPR=0.01): 100. Result ID: 69c29e6047f34ce924ab3f3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"QWEN 32B"}. This record does not assert independent reproduction. ### Ours TPR (FPR=0.01): 100. Result ID: 69c29e6047f34ce924ab3f42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"QWEN 32B"}. This record does not assert independent reproduction. ### Binoculars TPR (FPR=0.01): 99. Result ID: 69c29e6047f34ce924ab3f3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"GPT-NEOX Erebus"}. This record does not assert independent reproduction. ### Ours TPR (FPR=0.01): 99. Result ID: 69c29e6047f34ce924ab3f3c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"GPT-NEOX Erebus"}. This record does not assert independent reproduction. ### Binoculars TPR (FPR=0.01): 99. Result ID: 69c29e6047f34ce924ab3f41. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"QWEN 32B"}. This record does not assert independent reproduction. ### Binoculars TPR (FPR=0.01): 97. Result ID: 69c29e6047f34ce924ab3f35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"LLAMA 3 8B"}. This record does not assert independent reproduction. ### Ours TPR (FPR=0.01): 90. Result ID: 69c29e6047f34ce924ab3f36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"LLAMA 3 8B"}. This record does not assert independent reproduction. ### LogRank TPR (FPR=0.01): 54. Result ID: 69c29e6047f34ce924ab3f39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"GPT-NEOX Erebus"}. This record does not assert independent reproduction. ### Rank TPR (FPR=0.01): 49. Result ID: 69c29e6047f34ce924ab3f32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"LLAMA 3 8B"}. This record does not assert independent reproduction. ### log p(x) TPR (FPR=0.01): 46. Result ID: 69c29e6047f34ce924ab3f37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"GPT-NEOX Erebus"}. This record does not assert independent reproduction. ### Rank TPR (FPR=0.01): 43. Result ID: 69c29e6047f34ce924ab3f3e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"QWEN 32B"}. This record does not assert independent reproduction. ### Rank TPR (FPR=0.01): 39. Result ID: 69c29e6047f34ce924ab3f38. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Generator Model":"GPT-NEOX Erebus"}. This record does not assert independent reproduction. ### Entropy TPR (FPR=0.01): 0. Result ID: 69c29e6047f34ce924ab3f34. [Reporting paper]() Recorded evaluation configuration: {"Generator Model":"LLAMA 3 8B"}. This record does not assert independent reproduction. ### Entropy TPR (FPR=0.01): 0. Result ID: 69c29e6047f34ce924ab3f3a. [Reporting paper]() Recorded evaluation configuration: {"Generator Model":"GPT-NEOX Erebus"}. This record does not assert independent reproduction. ### Entropy TPR (FPR=0.01): 0. Result ID: 69c29e6047f34ce924ab3f40. [Reporting paper]() Recorded evaluation configuration: {"Generator Model":"QWEN 32B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.