# Open-ended generation (Medical Diagnostic QA) on RJUA (test) Source: [Open-ended generation (Medical Diagnostic QA) on RJUA (test)]() Collection index: [llms.txt]() Data updated: 2026-05-28T08:11:42.985Z Evaluation of model performance on the test split of the RJUA dataset for open-ended medical diagnostic question answering generation, measured using metrics like Rouge-L, Reranker scores, and RL/RR metrics. 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 | Open-ended generation (Medical Diagnostic QA) | | Dataset (including any stated split) | RJUA (test) | | Metric | Rouge-L | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Rouge-L](): Higher is better; unit: PERCENT. - [Reranker Score](): Higher is better; unit: PERCENT. - [RL@8](): Higher is better; unit: PERCENT. - [RR@8](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Rouge-L | Result date | Report paper | | --- | --- | --- | --- | | W-REINFORCE | 33.7 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 33.5 | Not recorded | 6a17cc2bdbd7150506f813f2 | | EAPO | 33 | Not recorded | 6a17cc2bdbd7150506f813f2 | | NSR | 32.7 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 32.2 | Not recorded | 6a17cc2bdbd7150506f813f2 | | GRPO | 31.2 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 30.2 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 30.1 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 29.9 | Not recorded | 6a17cc2bdbd7150506f813f2 | | PSR | 29.3 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 27.4 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 26.3 | Not recorded | 6a17cc2bdbd7150506f813f2 | | W-REINFORCE | 23.2 | Not recorded | 6a17cc2bdbd7150506f813f2 | ### W-REINFORCE Rouge-L: 33.7. Result ID: 6a17f7d3fbc373592c119137. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"0.2","w-":"1"}. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 33.5. Result ID: 6a17f7d3fbc373592c11913d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"1","w-":"5"}. This record does not assert independent reproduction. ### EAPO Rouge-L: 33. Result ID: 6a17f7d3fbc373592c11913e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NSR Rouge-L: 32.7. Result ID: 6a17f7d3fbc373592c119134. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 32.2. Result ID: 6a17f7d3fbc373592c119136. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"0.1","w-":"1"}. This record does not assert independent reproduction. ### GRPO Rouge-L: 31.2. Result ID: 6a17f7d3fbc373592c119132. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 30.2. Result ID: 6a17f7d3fbc373592c119139. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"5","w-":"1"}. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 30.1. Result ID: 6a17f7d3fbc373592c119138. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"1","w-":"1"}. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 29.9. Result ID: 6a17f7d3fbc373592c11913a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"1","w-":"0.05"}. This record does not assert independent reproduction. ### PSR Rouge-L: 29.3. Result ID: 6a17f7d3fbc373592c119133. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 27.4. Result ID: 6a17f7d3fbc373592c11913c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"1","w-":"0.2"}. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 26.3. Result ID: 6a17f7d3fbc373592c119135. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"0.05","w-":"1"}. This record does not assert independent reproduction. ### W-REINFORCE Rouge-L: 23.2. Result ID: 6a17f7d3fbc373592c11913b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"w+":"1","w-":"0.1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.