# Multi-attribute Conditional Text Generation on CompMCTG In-distribution Few-shot 1.0 (test) Source: [Multi-attribute Conditional Text Generation on CompMCTG In-distribution Few-shot 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:41.317Z Evaluation of Multi-attribute Conditional Text Generation performance on the test split of the CompMCTG dataset (In-distribution Few-shot 1.0 setting), measured using Accuracy and Perplexity. 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 | Multi-attribute Conditional Text Generation | | Dataset (including any stated split) | CompMCTG In-distribution Few-shot 1.0 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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. - [Perplexity](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Dis-Lens | 87.81 | Not recorded | 68fa73671e209131cea5c3a8 | | Prior | 85.19 | Not recorded | 68fa73671e209131cea5c3a8 | | Con. Prefix | 79.89 | Not recorded | 68fa73671e209131cea5c3a8 | | DCG | 78.89 | Not recorded | 68fa73671e209131cea5c3a8 | | CTRL | 77.87 | Not recorded | 68fa73671e209131cea5c3a8 | | LLaMA-2 | 62.78 | Not recorded | 68fa73671e209131cea5c3a8 | | CatPrompt | 62.47 | Not recorded | 68fa73671e209131cea5c3a8 | | Fudge | 58 | Not recorded | 68fa73671e209131cea5c3a8 | | ChatGPT | 56.64 | Not recorded | 68fa73671e209131cea5c3a8 | | PPLM | 43.07 | Not recorded | 68fa73671e209131cea5c3a8 | ### Dis-Lens Accuracy: 87.81. Result ID: 6992c7293a6c314849116caf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Separate-Training based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### Prior Accuracy: 85.19. Result ID: 6992c7293a6c314849116cb0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Separate-Training based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### Con. Prefix Accuracy: 79.89. Result ID: 6992c7293a6c314849116cb3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Joint-Training based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### DCG Accuracy: 78.89. Result ID: 6992c7293a6c314849116cb4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Joint-Training based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### CTRL Accuracy: 77.87. Result ID: 6992c7293a6c314849116cb1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Joint-Training based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### LLaMA-2 Accuracy: 62.78. Result ID: 6992c7293a6c314849116cab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"LLM+In-context Learning","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### CatPrompt Accuracy: 62.47. Result ID: 6992c7293a6c314849116cb2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Joint-Training based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### Fudge Accuracy: 58. Result ID: 6992c7293a6c314849116cae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Decoding-Time based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### ChatGPT Accuracy: 56.64. Result ID: 6992c7293a6c314849116cac. [Reporting paper]() Recorded evaluation configuration: {"Category":"LLM+In-context Learning","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. ### PPLM Accuracy: 43.07. Result ID: 6992c7293a6c314849116cad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Decoding-Time based","Evaluation Protocol":"Few-Shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.