# Contextual Question Answering on Gemma-2B-IT 5% forget set Source: [Contextual Question Answering on Gemma-2B-IT 5% forget set]() Collection index: [llms.txt]() Data updated: 2026-05-28T06:51:18.945Z Evaluation of model performance on the Gemma-2B-IT 5% forget set for Contextual Question Answering, measured using ROUGE-L and LLM-Judge. 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 | Contextual Question Answering | | Dataset (including any stated split) | Gemma-2B-IT 5% forget set | | Metric | ROUGE-L | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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. - [LLM Judge Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | ROUGE-L | Result date | Report paper | | --- | --- | --- | --- | | PDU | 92.4 | Not recorded | 68fa7c5d1e209131cea8dbff | | GradDiff | 86.8 | Not recorded | 68fa7c5d1e209131cea8dbff | | SimNPO | 76.5 | Not recorded | 68fa7c5d1e209131cea8dbff | | DPO | 74.9 | Not recorded | 68fa7c5d1e209131cea8dbff | | SimNPO | 70.6 | Not recorded | 68fa7c5d1e209131cea8dbff | | DPO | 40.5 | Not recorded | 68fa7c5d1e209131cea8dbff | | PDU | 3 | Not recorded | 68fa7c5d1e209131cea8dbff | | GradDiff | 0.1 | Not recorded | 68fa7c5d1e209131cea8dbff | ### PDU ROUGE-L: 92.4. Result ID: 6a17e435fbc373592c110b2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction. ### GradDiff ROUGE-L: 86.8. Result ID: 6a17e435fbc373592c110b29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction. ### SimNPO ROUGE-L: 76.5. Result ID: 6a17e435fbc373592c110b2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction. ### DPO ROUGE-L: 74.9. Result ID: 6a17e435fbc373592c110b27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Context-aware"}. This record does not assert independent reproduction. ### SimNPO ROUGE-L: 70.6. Result ID: 6a17e435fbc373592c110b2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction. ### DPO ROUGE-L: 40.5. Result ID: 6a17e435fbc373592c110b26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction. ### PDU ROUGE-L: 3. Result ID: 6a17e435fbc373592c110b2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction. ### GradDiff ROUGE-L: 0.1. Result ID: 6a17e435fbc373592c110b28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Vanilla"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.