# Narrative Question Answering on NarQA Source: [Narrative Question Answering on NarQA]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:00:41.944Z Evaluation of Narrative Question Answering performance on the NarQA dataset using generation metrics such as ROUGE-L and BLEU. 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 | Narrative Question Answering | | Dataset (including any stated split) | NarQA | | Metric | ROUGE-L | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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. - [BLEU](): Higher is better; unit: PERCENT. ## Recorded results | Method | ROUGE-L | Result date | Report paper | | --- | --- | --- | --- | | OLTQA | 57.59 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 57.34 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 56.89 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 56.87 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 56.63 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 56.04 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 55.86 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 54.68 | Not recorded | 68fa6f471e209131cea44b64 | | Hyperformer++ | 51.88 | Not recorded | 68fa6f471e209131cea44b64 | | EPR | 46.02 | Not recorded | 68fa6f471e209131cea44b64 | | Muppet | 45.3 | Not recorded | 68fa6f471e209131cea44b64 | | UnifiedQA | 44.69 | Not recorded | 68fa6f471e209131cea44b64 | | OLTQA | 44.56 | Not recorded | 68fa6f471e209131cea44b64 | | ProQA | 34.2 | Not recorded | 68fa6f471e209131cea44b64 | ### OLTQA ROUGE-L: 57.59. Result ID: 6990b35f3a6c314849028d5e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Configuration":"Full"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 57.34. Result ID: 6990b35f3a6c314849028d5c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Knowledge Distillation":"Static MKD"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 56.89. Result ID: 6990b35f3a6c314849028d56. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ablation":"without Pm"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 56.87. Result ID: 6990b35f3a6c314849028d5a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Retriever":"EPR"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 56.63. Result ID: 6990b35f3a6c314849028d59. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Retriever":"BM25"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 56.04. Result ID: 6990b35f3a6c314849028d5b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Re-ranker":"excluded"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 55.86. Result ID: 6990b35f3a6c314849028d58. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Knowledge Distillation":"without MKD"}. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 54.68. Result ID: 6990b35f3a6c314849028d5d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Knowledge Distillation":"Back KD"}. This record does not assert independent reproduction. ### Hyperformer++ ROUGE-L: 51.88. Result ID: 6990b35f3a6c314849028d54. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### EPR ROUGE-L: 46.02. Result ID: 6990b35f3a6c314849028d55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Muppet ROUGE-L: 45.3. Result ID: 6990b35f3a6c314849028d53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UnifiedQA ROUGE-L: 44.69. Result ID: 6990b35f3a6c314849028d51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OLTQA ROUGE-L: 44.56. Result ID: 6990b35f3a6c314849028d57. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ablation":"without Pk"}. This record does not assert independent reproduction. ### ProQA ROUGE-L: 34.2. Result ID: 6990b35f3a6c314849028d52. [Reporting paper]() [Method origin 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.