# Claim Improvement Suggestion and Optimal Claim Detection on Argumentative Claims Dataset Source: [Claim Improvement Suggestion and Optimal Claim Detection on Argumentative Claims Dataset]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:55.010Z Evaluation of model performance on suggesting improvements for argumentative claims and identifying the optimal claim, measured using Accuracy, Macro F1, and specialized F1 scores for clarification, typos, links, and optimality. 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 | Claim Improvement Suggestion and Optimal Claim Detection | | Dataset (including any stated split) | Argumentative Claims Dataset | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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. - [Macro F1](): Higher is better; unit: PERCENT. - [F1 (Clarification)](): Higher is better; unit: PERCENT. - [F1 (Typo)](): Higher is better; unit: PERCENT. - [F1 (Links)](): Higher is better; unit: PERCENT. - [F1 (Optimal)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | FT-DeBERTa | 65.5 | Not recorded | 68fa6f801e209131cea46090 | | FT-DeBERTa | 64.8 | Not recorded | 68fa6f801e209131cea46090 | | FT-DeBERTa | 64.2 | Not recorded | 68fa6f801e209131cea46090 | | FT-ELECTRA | 63.3 | Not recorded | 68fa6f801e209131cea46090 | | FT-ELECTRA | 62.9 | Not recorded | 68fa6f801e209131cea46090 | | FT-ELECTRA | 62.7 | Not recorded | 68fa6f801e209131cea46090 | | Random baseline | 25 | Not recorded | 68fa6f801e209131cea46090 | ### FT-DeBERTa Accuracy: 65.5. Result ID: 6990c75c3a6c314849033b28. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context":"Thesis Statement"}. This record does not assert independent reproduction. ### FT-DeBERTa Accuracy: 64.8. Result ID: 6990c75c3a6c314849033b27. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context":"Parent Claim"}. This record does not assert independent reproduction. ### FT-DeBERTa Accuracy: 64.2. Result ID: 6990c75c3a6c314849033b26. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context":"None"}. This record does not assert independent reproduction. ### FT-ELECTRA Accuracy: 63.3. Result ID: 6990c75c3a6c314849033b25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context":"Thesis Statement"}. This record does not assert independent reproduction. ### FT-ELECTRA Accuracy: 62.9. Result ID: 6990c75c3a6c314849033b24. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context":"Parent Claim"}. This record does not assert independent reproduction. ### FT-ELECTRA Accuracy: 62.7. Result ID: 6990c75c3a6c314849033b23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Context":"None"}. This record does not assert independent reproduction. ### Random baseline Accuracy: 25. Result ID: 6990c75c3a6c314849033b29. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.