# Pareto prompt set identification on CNN/DailyMail Source: [Pareto prompt set identification on CNN/DailyMail]() Collection index: [llms.txt]() Data updated: 2026-05-15T08:42:43.163Z Evaluation of Pareto prompt set identification performance on the CNN/DailyMail dataset, measured using Human Value (HV) metrics across different Pareto frontier sizes (b=3, 5, 8, 10). 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 | Pareto prompt set identification | | Dataset (including any stated split) | CNN/DailyMail | | Metric | Hypervolume (HV) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 54 of 54 | | 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 - [Hypervolume (HV)](): Higher is better; unit: PERCENT. - [HV (b=3)](): Higher is better; unit: PERCENT. - [HV (b=5)](): Higher is better; unit: PERCENT. - [HV (b=8)](): Higher is better; unit: PERCENT. - [HV (b=10)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Hypervolume (HV) | Result date | Report paper | | --- | --- | --- | --- | | MLP-EGE | 18.03 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 17.54 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 17.53 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 17.44 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 17.27 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 17.2 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 17.16 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 17.06 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.99 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 16.9 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.88 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 16.85 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.84 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 16.8 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.73 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.71 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 16.61 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 16.51 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 16.47 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 16.46 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 16.39 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.32 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 16.31 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.28 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.28 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 16.24 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 16.18 | Not recorded | 6a06a87cdbc836b87d829f83 | | MLP-EGE | 16.18 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 16.03 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 15.79 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 15.77 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 15.59 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 15.43 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 15.34 | Not recorded | 6a06a87cdbc836b87d829f83 | | Uniform | 15.19 | Not recorded | 6a06a87cdbc836b87d829f83 | | EGE | 15.03 | Not recorded | 6a06a87cdbc836b87d829f83 | ### MLP-EGE Hypervolume (HV): 18.03. Result ID: 6a06dc7447f34ce924ee9002. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 17.54. Result ID: 6a06dc7447f34ce924ee9017. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 17.53. Result ID: 6a06dc7447f34ce924ee8ffe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 17.44. Result ID: 6a06dc7447f34ce924ee8fff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 17.27. Result ID: 6a06dc7447f34ce924ee9003. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 17.2. Result ID: 6a06dc7447f34ce924ee900b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 17.16. Result ID: 6a06dc7447f34ce924ee901b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 17.06. Result ID: 6a06dc7447f34ce924ee900a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.99. Result ID: 6a06dc7447f34ce924ee901a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 16.9. Result ID: 6a06dc7447f34ce924ee9016. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.88. Result ID: 6a06dc7447f34ce924ee9001. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 16.85. Result ID: 6a06dc7447f34ce924ee8ffa. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.84. Result ID: 6a06dc7447f34ce924ee9019. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 16.8. Result ID: 6a06dc7447f34ce924ee8ffd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.73. Result ID: 6a06dc7447f34ce924ee900f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.71. Result ID: 6a06dc7447f34ce924ee900e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 16.61. Result ID: 6a06dc7447f34ce924ee8ffb. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 16.51. Result ID: 6a06dc7447f34ce924ee9008. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 16.47. Result ID: 6a06dc7447f34ce924ee9009. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 16.46. Result ID: 6a06dc7447f34ce924ee9007. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 16.39. Result ID: 6a06dc7447f34ce924ee9015. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.32. Result ID: 6a06dc7447f34ce924ee9000. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 16.31. Result ID: 6a06dc7447f34ce924ee9013. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"10","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.28. Result ID: 6a06dc7447f34ce924ee900d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.28. Result ID: 6a06dc7447f34ce924ee9018. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 16.24. Result ID: 6a06dc7447f34ce924ee9012. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 16.18. Result ID: 6a06dc7447f34ce924ee9006. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"8","Model":"Llama 3"}. This record does not assert independent reproduction. ### MLP-EGE Hypervolume (HV): 16.18. Result ID: 6a06dc7447f34ce924ee900c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 16.03. Result ID: 6a06dc7447f34ce924ee8ffc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 15.79. Result ID: 6a06dc7447f34ce924ee9011. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 15.77. Result ID: 6a06dc7447f34ce924ee8ff8. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 15.59. Result ID: 6a06dc7447f34ce924ee9004. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 15.43. Result ID: 6a06dc7447f34ce924ee9005. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"50","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 15.34. Result ID: 6a06dc7447f34ce924ee8ff9. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"30","b (Per-arm budget)":"5","Model":"Llama 3"}. This record does not assert independent reproduction. ### Uniform Hypervolume (HV): 15.19. Result ID: 6a06dc7447f34ce924ee9010. [Reporting paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. ### EGE Hypervolume (HV): 15.03. Result ID: 6a06dc7447f34ce924ee9014. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"K (Prompt set size)":"100","b (Per-arm budget)":"3","Model":"Llama 3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.