# Factual Consistency Evaluation on FRANK-XSum (FRK-X) Source: [Factual Consistency Evaluation on FRANK-XSum (FRK-X)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:34.692Z Evaluation of model factual consistency on the FRANK-XSum (FRK-X) dataset, measured using Spearman correlation. 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 | Factual Consistency Evaluation | | Dataset (including any stated split) | FRANK-XSum (FRK-X) | | Metric | Spearman Correlation | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 30 of 30 | | 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 - [Spearman Correlation](): Higher is better; unit: SCALAR. ## Recorded results | Method | Spearman Correlation | Result date | Report paper | | --- | --- | --- | --- | | DAE | 32.1 | Not recorded | 68fa6f801e209131cea4607f | | ALIGN | 30 | Not recorded | 68fa71131e209131cea4f1ee | | ALIGNSCORE-large | 29 | Not recorded | 68fa6f801e209131cea4607f | | ALIGNSCORE-base | 28 | Not recorded | 68fa6f801e209131cea4607f | | UniEval | 26.7 | Not recorded | 68fa6f801e209131cea4607f | | UniEval | 26.7 | Not recorded | 68fa71131e209131cea4f1ee | | QAFactEval | 25.5 | Not recorded | 68fa6f801e209131cea4607f | | QAFactEval | 25.5 | Not recorded | 68fa71131e209131cea4f1ee | | ALIGN | 25.5 | Not recorded | 68fa71131e209131cea4f1ee | | CTC | 20.4 | Not recorded | 68fa6f801e209131cea4607f | | CTC | 20.4 | Not recorded | 68fa71131e209131cea4f1ee | | BARTScore | 20 | Not recorded | 68fa6f801e209131cea4607f | | BARTScore | 20 | Not recorded | 68fa71131e209131cea4f1ee | | QuestEval | 19.1 | Not recorded | 68fa6f801e209131cea4607f | | BLEURT | 13.9 | Not recorded | 68fa6f801e209131cea4607f | | BLEURT | 13.9 | Not recorded | 68fa71131e209131cea4f1ee | | SimCSE | 13.3 | Not recorded | 68fa6f801e209131cea4607f | | SummaC-ZS | 12.8 | Not recorded | 68fa6f801e209131cea4607f | | BERTScore | 12.7 | Not recorded | 68fa6f801e209131cea4607f | | BERTScore | 12.7 | Not recorded | 68fa71131e209131cea4f1ee | | MNLI | 11.7 | Not recorded | 68fa6f801e209131cea4607f | | NER-Overlap | 11.3 | Not recorded | 68fa6f801e209131cea4607f | | SummaC-CONV | 11 | Not recorded | 68fa6f801e209131cea4607f | | ROUGE-L | 8.2 | Not recorded | 68fa6f801e209131cea4607f | | FactCC | 7.9 | Not recorded | 68fa6f801e209131cea4607f | | BLANC | 6.5 | Not recorded | 68fa6f801e209131cea4607f | | BLEU | 6.3 | Not recorded | 68fa6f801e209131cea4607f | | ROUGE-1 | 5.6 | Not recorded | 68fa6f801e209131cea4607f | | ROUGE-2 | 2.8 | Not recorded | 68fa6f801e209131cea4607f | | FEQA | 1.5 | Not recorded | 68fa6f801e209131cea4607f | ### DAE Spearman Correlation: 32.1. Result ID: 6990c73d3a6c314849033586. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"NLI"}. This record does not assert independent reproduction. ### ALIGN Spearman Correlation: 30. Result ID: 699197373a6c3148490930f4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model size":"large"}. This record does not assert independent reproduction. ### ALIGNSCORE-large Spearman Correlation: 29. Result ID: 6990c73d3a6c31484903358f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Ours"}. This record does not assert independent reproduction. ### ALIGNSCORE-base Spearman Correlation: 28. Result ID: 6990c73d3a6c31484903358e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Ours"}. This record does not assert independent reproduction. ### UniEval Spearman Correlation: 26.7. Result ID: 6990c73d3a6c314849033589. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Misc"}. This record does not assert independent reproduction. ### UniEval Spearman Correlation: 26.7. Result ID: 699197373a6c3148490930f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### QAFactEval Spearman Correlation: 25.5. Result ID: 6990c73d3a6c31484903357c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"QA"}. This record does not assert independent reproduction. ### QAFactEval Spearman Correlation: 25.5. Result ID: 699197373a6c3148490930f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ALIGN Spearman Correlation: 25.5. Result ID: 699197373a6c3148490930f3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model size":"base"}. This record does not assert independent reproduction. ### CTC Spearman Correlation: 20.4. Result ID: 6990c73d3a6c31484903358a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Misc"}. This record does not assert independent reproduction. ### CTC Spearman Correlation: 20.4. Result ID: 699197373a6c3148490930f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### BARTScore Spearman Correlation: 20. Result ID: 6990c73d3a6c31484903358b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Misc"}. This record does not assert independent reproduction. ### BARTScore Spearman Correlation: 20. Result ID: 699197373a6c3148490930ef. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### QuestEval Spearman Correlation: 19.1. Result ID: 6990c73d3a6c31484903357b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"QA"}. This record does not assert independent reproduction. ### BLEURT Spearman Correlation: 13.9. Result ID: 6990c73d3a6c314849033584. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Regression"}. This record does not assert independent reproduction. ### BLEURT Spearman Correlation: 13.9. Result ID: 699197373a6c3148490930ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SimCSE Spearman Correlation: 13.3. Result ID: 6990c73d3a6c314849033583. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### SummaC-ZS Spearman Correlation: 12.8. Result ID: 6990c73d3a6c314849033587. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"NLI"}. This record does not assert independent reproduction. ### BERTScore Spearman Correlation: 12.7. Result ID: 6990c73d3a6c314849033581. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### BERTScore Spearman Correlation: 12.7. Result ID: 699197373a6c3148490930ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MNLI Spearman Correlation: 11.7. Result ID: 6990c73d3a6c314849033585. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"NLI"}. This record does not assert independent reproduction. ### NER-Overlap Spearman Correlation: 11.3. Result ID: 6990c73d3a6c314849033582. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### SummaC-CONV Spearman Correlation: 11. Result ID: 6990c73d3a6c314849033588. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"NLI"}. This record does not assert independent reproduction. ### ROUGE-L Spearman Correlation: 8.2. Result ID: 6990c73d3a6c31484903357f. [Reporting paper]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### FactCC Spearman Correlation: 7.9. Result ID: 6990c73d3a6c31484903358c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Misc"}. This record does not assert independent reproduction. ### BLANC Spearman Correlation: 6.5. Result ID: 6990c73d3a6c31484903358d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Misc"}. This record does not assert independent reproduction. ### BLEU Spearman Correlation: 6.3. Result ID: 6990c73d3a6c314849033580. [Reporting paper]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### ROUGE-1 Spearman Correlation: 5.6. Result ID: 6990c73d3a6c31484903357d. [Reporting paper]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### ROUGE-2 Spearman Correlation: 2.8. Result ID: 6990c73d3a6c31484903357e. [Reporting paper]() Recorded evaluation configuration: {"Type":"Similarity Matching"}. This record does not assert independent reproduction. ### FEQA Spearman Correlation: 1.5. Result ID: 6990c73d3a6c31484903357a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"QA"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.