# Commonsense Validation and Explanation on ComVE (test) Source: [Commonsense Validation and Explanation on ComVE (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:55.390Z Evaluation of model performance on the test split of the ComVE dataset for Commonsense Validation and Explanation, measured by Accuracy and faithfulness 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 | Commonsense Validation and Explanation | | Dataset (including any stated split) | ComVE (test) | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [CT Unfaithfulness](): Lower is better; unit: PERCENT. - [CCT Faithfulness](): Higher is better; unit: SCALAR. - [nBERTs Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Llama2-70B | 98.5 | Not recorded | 68fa738f1e209131cea5d3bb | | Llama2-70B | 97.7 | Not recorded | 68fa738f1e209131cea5d3bb | | Llama2-13B | 75.8 | Not recorded | 68fa738f1e209131cea5d3bb | | Llama2-13B | 75.6 | Not recorded | 68fa738f1e209131cea5d3bb | | SPARSEFIT (Att.Q+LN) | 74.86 | Not recorded | 68fa74701e209131cea61c52 | | AdaLoRA (1.15%) | 69.66 | Not recorded | 68fa74701e209131cea61c52 | | LoRA (Att.KQVO, Rank=4) | 68.96 | Not recorded | 68fa74701e209131cea61c52 | | LoRA (Att.QV, Rank=128) | 67.77 | Not recorded | 68fa74701e209131cea61c52 | | (IA)³ | 58.53 | Not recorded | 68fa74701e209131cea61c52 | | Llama2-7B | 55.2 | Not recorded | 68fa738f1e209131cea5d3bb | | Llama2-7B | 52.4 | Not recorded | 68fa738f1e209131cea5d3bb | | Random | 50 | Not recorded | 68fa738f1e209131cea5d3bb | | AdaLoRA (4.48%) | 19.43 | Not recorded | 68fa74701e209131cea61c52 | ### Llama2-70B Accuracy: 98.5. Result ID: 6992f1e53a6c314849128d21. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Order":"explain-then-predict (EP)"}. This record does not assert independent reproduction. ### Llama2-70B Accuracy: 97.7. Result ID: 6992f1e53a6c314849128d20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Order":"predict-then-explain (PE)"}. This record does not assert independent reproduction. ### Llama2-13B Accuracy: 75.8. Result ID: 6992f1e53a6c314849128d1f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Order":"explain-then-predict (EP)"}. This record does not assert independent reproduction. ### Llama2-13B Accuracy: 75.6. Result ID: 6992f1e53a6c314849128d1e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Order":"predict-then-explain (PE)"}. This record does not assert independent reproduction. ### SPARSEFIT (Att.Q+LN) Accuracy: 74.86. Result ID: 69935ccd3a6c3148491568af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Parameters":"6.84%","FLOPS":"2.37e14","Base Model":"T5-large","Few-shot splits":60}. This record does not assert independent reproduction. ### AdaLoRA (1.15%) Accuracy: 69.66. Result ID: 69935ccd3a6c3148491568b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Parameters":"1.15%","FLOPS":"1.48e15","Base Model":"T5-large","Few-shot splits":60}. This record does not assert independent reproduction. ### LoRA (Att.KQVO, Rank=4) Accuracy: 68.96. Result ID: 69935ccd3a6c3148491568b3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Trainable Parameters":"0.32%","FLOPS":"2.75e14","Base Model":"T5-large","Few-shot splits":60}. This record does not assert independent reproduction. ### LoRA (Att.QV, Rank=128) Accuracy: 67.77. Result ID: 69935ccd3a6c3148491568b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Trainable Parameters":"4.86%","FLOPS":"2.88e14","Base Model":"T5-large","Few-shot splits":60}. This record does not assert independent reproduction. ### (IA)³ Accuracy: 58.53. Result ID: 69935ccd3a6c3148491568b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Trainable Parameters":"0.07%","FLOPS":"2.74e14","Base Model":"T5-large","Few-shot splits":60}. This record does not assert independent reproduction. ### Llama2-7B Accuracy: 55.2. Result ID: 6992f1e53a6c314849128d1c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Order":"predict-then-explain (PE)"}. This record does not assert independent reproduction. ### Llama2-7B Accuracy: 52.4. Result ID: 6992f1e53a6c314849128d1d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Prompt Order":"explain-then-predict (EP)"}. This record does not assert independent reproduction. ### Random Accuracy: 50. Result ID: 6992f1e53a6c314849128d22. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AdaLoRA (4.48%) Accuracy: 19.43. Result ID: 69935ccd3a6c3148491568b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Trainable Parameters":"4.48%","FLOPS":"2.87e14","Base Model":"T5-large","Few-shot splits":60}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.