# Long-form Question Answering on ALCE LFQA Source: [Long-form Question Answering on ALCE LFQA]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:00:42.253Z Evaluation of model performance on the ALCE LFQA dataset for Long-form Question Answering, measured using ROUGE-L, BERTSCORE, and other custom 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 | Long-form Question Answering | | Dataset (including any stated split) | ALCE LFQA | | Metric | ROUGE-L | | 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 - [ROUGE-L](): Higher is better; unit: PERCENT. - [BERTScore](): Higher is better; unit: PERCENT. - [AutoAIS](): Higher is better; unit: SCALAR. - [Output Length](): Higher is better; unit: SCALAR. - [No Attention (%)](): Lower is better; unit: PERCENT. ## Recorded results | Method | ROUGE-L | Result date | Report paper | | --- | --- | --- | --- | | ATTR. FIRST\_CoT | 38.6 | Not recorded | 68fa74061e209131cea5f4f2 | | ATTR. FIRST | 35.8 | Not recorded | 68fa74061e209131cea5f4f2 | | ALCE | 35.2 | Not recorded | 68fa74061e209131cea5f4f2 | | GEMINI | 33.1 | Not recorded | 68fa74061e209131cea5f4f2 | | PRIMERA | 32.2 | Not recorded | 68fa74061e209131cea5f4f2 | | ATTR. FIRST\_joint | 27 | Not recorded | 68fa74061e209131cea5f4f2 | | ATTR. FIRST | 24.7 | Not recorded | 68fa74061e209131cea5f4f2 | ### ATTR. FIRST\_CoT ROUGE-L: 38.6. Result ID: 699315503a6c3148491395b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"ICL","Chain-of-Thought":true}. This record does not assert independent reproduction. ### ATTR. FIRST ROUGE-L: 35.8. Result ID: 699315503a6c3148491395b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"ICL"}. This record does not assert independent reproduction. ### ALCE ROUGE-L: 35.2. Result ID: 699315503a6c3148491395b7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"ICL"}. This record does not assert independent reproduction. ### GEMINI ROUGE-L: 33.1. Result ID: 699315503a6c3148491395b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"ICL"}. This record does not assert independent reproduction. ### PRIMERA ROUGE-L: 32.2. Result ID: 699315503a6c3148491395ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"FT"}. This record does not assert independent reproduction. ### ATTR. FIRST\_joint ROUGE-L: 27. Result ID: 699315503a6c3148491395bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"FT","Training":"joint"}. This record does not assert independent reproduction. ### ATTR. FIRST ROUGE-L: 24.7. Result ID: 699315503a6c3148491395bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"FT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.