# Rule-of-Thumb Generation on MIC

Source: [Rule-of-Thumb Generation on MIC](<https://www.sota2.com/research/sota/rule-of-thumb-generation-on-mic>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:08:49.426Z

Evaluation of models generating rule-of-thumb statements based on the MIC dataset, assessed using metrics like Well-formedness, Fluency, Relevance, and Global Consensus.

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 |
| Metric | Well-formedness |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Well-formedness](<https://www.sota2.com/research/sota/rule-of-thumb-generation-on-mic.md?metric=Well-formedness>): Higher is better; unit: SCALAR.

- [Fluency](<https://www.sota2.com/research/sota/rule-of-thumb-generation-on-mic.md?metric=Fluency>): Higher is better; unit: SCALAR.

- [Relevance](<https://www.sota2.com/research/sota/rule-of-thumb-generation-on-mic.md?metric=Relevance>): Higher is better; unit: SCALAR.

- [Global Consensus](<https://www.sota2.com/research/sota/rule-of-thumb-generation-on-mic.md?metric=Global%20Consensus>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Well-formedness | Result date | Report paper |
| --- | --- | --- | --- |
| Alignedd-PM | 0.568 | Not recorded | 68fa71cd1e209131cea53088 |
| Alignedsoft | 0.55 | Not recorded | 68fa71cd1e209131cea53088 |
| Base | 0.528 | Not recorded | 68fa71cd1e209131cea53088 |

### Alignedd-PM

Well-formedness: 0.568. Result ID: 6991e52b3a6c3148490b4962.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71cd1e209131cea53088.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71cd1e209131cea53088.md>)

[Implementation](<https://github.com/wangjs9/Aligned-dPM>)

Recorded evaluation configuration: {"Backbone":"BART-large","Decoding Strategy":"beam"}. This record does not assert independent reproduction.

### Alignedsoft

Well-formedness: 0.55. Result ID: 6991e52b3a6c3148490b4961.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71cd1e209131cea53088.md>)

Recorded evaluation configuration: {"Backbone":"BART-large","Decoding Strategy":"beam"}. This record does not assert independent reproduction.

### Base

Well-formedness: 0.528. Result ID: 6991e52b3a6c3148490b4960.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71cd1e209131cea53088.md>)

Recorded evaluation configuration: {"Backbone":"BART-large","Decoding Strategy":"beam"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.