# Rule-of-Thumb Generation on MIC (test) Source: [Rule-of-Thumb Generation on MIC (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:59:12.683Z Evaluation of generative models producing rule-of-thumb statements on the test split of the MIC dataset, measured using ROUGE scores (R-1, R-2, R-L), BertScore, and ScareBLEU. 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 | Rule-of-Thumb Generation | | Dataset (including any stated split) | MIC (test) | | Metric | R-1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 - [R-1](): Higher is better; unit: PERCENT. - [R-2](): Higher is better; unit: PERCENT. - [R-L](): Higher is better; unit: PERCENT. - [BertScore](): Higher is better; unit: PERCENT. - [ScareBLEU](): Higher is better; unit: PERCENT. - [Avg.Len](): Higher is better; unit: SCALAR. ## Recorded results | Method | R-1 | Result date | Report paper | | --- | --- | --- | --- | | Alignedd-PM | 55.18 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 55.07 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 55.05 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 54.86 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 54.82 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 54.82 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 54.81 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 54.81 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 54.77 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 54.77 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 54.65 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 54.54 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 53.45 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 53.44 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 52.14 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 41.78 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 41.44 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 41.41 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 41.41 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 40.9 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 40.22 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 38.34 | Not recorded | 68fa71cd1e209131cea53088 | | Alignedd-PM | 38.15 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 37.94 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 37.84 | Not recorded | 68fa71cd1e209131cea53088 | | Aligned\_soft | 37.77 | Not recorded | 68fa71cd1e209131cea53088 | | Base | 37.04 | Not recorded | 68fa71cd1e209131cea53088 | ### Alignedd-PM R-1: 55.18. Result ID: 6991e52b3a6c3148490b496e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Base R-1: 55.07. Result ID: 6991e52b3a6c3148490b496c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 55.05. Result ID: 6991e52b3a6c3148490b4977. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 54.86. Result ID: 6991e52b3a6c3148490b497d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 54.82. Result ID: 6991e52b3a6c3148490b496d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 54.82. Result ID: 6991e52b3a6c3148490b4976. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Base R-1: 54.81. Result ID: 6991e52b3a6c3148490b4975. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 54.81. Result ID: 6991e52b3a6c3148490b497a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Base R-1: 54.77. Result ID: 6991e52b3a6c3148490b4978. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Base R-1: 54.77. Result ID: 6991e52b3a6c3148490b497b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 54.65. Result ID: 6991e52b3a6c3148490b497c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 54.54. Result ID: 6991e52b3a6c3148490b4979. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"BART (Large)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 53.45. Result ID: 6991e52b3a6c3148490b4965. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Base R-1: 53.44. Result ID: 6991e52b3a6c3148490b4963. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 52.14. Result ID: 6991e52b3a6c3148490b4964. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"Beam"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 41.78. Result ID: 6991e52b3a6c3148490b4974. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 41.44. Result ID: 6991e52b3a6c3148490b4973. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 41.41. Result ID: 6991e52b3a6c3148490b496b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Base R-1: 41.41. Result ID: 6991e52b3a6c3148490b4972. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 40.9. Result ID: 6991e52b3a6c3148490b496a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Base R-1: 40.22. Result ID: 6991e52b3a6c3148490b4969. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"p=0.9"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 38.34. Result ID: 6991e52b3a6c3148490b4971. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Alignedd-PM R-1: 38.15. Result ID: 6991e52b3a6c3148490b4968. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Base R-1: 37.94. Result ID: 6991e52b3a6c3148490b496f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 37.84. Result ID: 6991e52b3a6c3148490b4970. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Flan-T5 (Base)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Aligned\_soft R-1: 37.77. Result ID: 6991e52b3a6c3148490b4967. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. ### Base R-1: 37.04. Result ID: 6991e52b3a6c3148490b4966. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"T5 (Small)","Decoding Strategy":"Greedy"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.