# Faithful Narrative Generation on stroke Source: [Faithful Narrative Generation on stroke]() Collection index: [llms.txt]() Data updated: 2026-03-23T11:44:27.260Z Evaluation of models on the 'stroke' dataset focusing on Faithful Narrative Generation, assessed using metrics like RA, SA, VA, and the count of Unfaithful Narratives. 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 | Faithful Narrative Generation | | Dataset (including any stated split) | stroke | | Metric | RA | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [RA](): Higher is better; unit: SCALAR. - [SA](): Higher is better; unit: SCALAR. - [VA](): Higher is better; unit: SCALAR. - [Count of Unfaithful Narratives](): Lower is better; unit: SCALAR. ## Recorded results | Method | RA | Result date | Report paper | | --- | --- | --- | --- | | Basic Design | 1 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Basic Design | 0.988 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Critic Design | 0.975 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Critic Design | 0.975 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Critic-Rule Design | 0.975 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Critic-Rule Design | 0.975 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Basic Design | 0.95 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Critic Design | 0.95 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Critic-Rule Design | 0.95 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Coherent Design | 0.95 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Coherent-Rule Design | 0.95 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Coherent Design | 0.938 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Coherent-Rule Design | 0.938 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Baseline | 0.925 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Coherent-Rule Design | 0.863 | Not recorded | 69c0c8ee0636e5bf4afc3aba | | Coherent Design | 0.838 | Not recorded | 69c0c8ee0636e5bf4afc3aba | ### Basic Design RA: 1. Result ID: 69c1274047f34ce924a9b484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Basic Design","Round":"2","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Basic Design RA: 0.988. Result ID: 69c1274047f34ce924a9b483. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Basic Design","Round":"1","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Critic Design RA: 0.975. Result ID: 69c1274047f34ce924a9b486. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Critic Design","Round":"1","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Critic Design RA: 0.975. Result ID: 69c1274047f34ce924a9b487. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Critic Design","Round":"2","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Critic-Rule Design RA: 0.975. Result ID: 69c1274047f34ce924a9b489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Critic-Rule Design","Round":"1","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Critic-Rule Design RA: 0.975. Result ID: 69c1274047f34ce924a9b48a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Critic-Rule Design","Round":"2","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Basic Design RA: 0.95. Result ID: 69c1274047f34ce924a9b482. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Basic Design","Round":"0","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Critic Design RA: 0.95. Result ID: 69c1274047f34ce924a9b485. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Critic Design","Round":"0","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Critic-Rule Design RA: 0.95. Result ID: 69c1274047f34ce924a9b488. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Critic-Rule Design","Round":"0","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Coherent Design RA: 0.95. Result ID: 69c1274047f34ce924a9b48b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Coherent Design","Round":"0","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Coherent-Rule Design RA: 0.95. Result ID: 69c1274047f34ce924a9b48e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Coherent-Rule Design","Round":"0","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Coherent Design RA: 0.938. Result ID: 69c1274047f34ce924a9b48c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Coherent Design","Round":"1","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Coherent-Rule Design RA: 0.938. Result ID: 69c1274047f34ce924a9b48f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Coherent-Rule Design","Round":"1","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Baseline RA: 0.925. Result ID: 69c1274047f34ce924a9b481. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Baseline","Round":"0","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Coherent-Rule Design RA: 0.863. Result ID: 69c1274047f34ce924a9b490. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Coherent-Rule Design","Round":"2","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. ### Coherent Design RA: 0.838. Result ID: 69c1274047f34ce924a9b48d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Design":"Coherent Design","Round":"2","Backbone":"Claude Sonnet 4.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.