# Multilingual Multi-hop Question Answering on 2WikiMultiHopQA (sampled 1k val) Source: [Multilingual Multi-hop Question Answering on 2WikiMultiHopQA (sampled 1k val)]() Collection index: [llms.txt]() Data updated: 2026-03-20T10:27:12.273Z Evaluation of multilingual multi-hop question answering performance using a specific 1,000-question sample from the validation split of the 2WikiMultiHopQA dataset. 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 | Multilingual Multi-hop Question Answering | | Dataset (including any stated split) | 2WikiMultiHopQA sampled 1,000 questions (val) | | Metric | EM (Swedish) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [EM (Swedish)](): Higher is better; unit: PERCENT. - [F1 (Swedish)](): Higher is better; unit: PERCENT. - [EM (Thai)](): Higher is better; unit: PERCENT. - [F1 (Thai)](): Higher is better; unit: PERCENT. - [EM (German)](): Higher is better; unit: PERCENT. - [F1 (German)](): Higher is better; unit: PERCENT. - [EM (Spanish)](): Higher is better; unit: PERCENT. - [F1 (Spanish)](): Higher is better; unit: PERCENT. - [EM (Chinese)](): Higher is better; unit: PERCENT. - [F1 (Chinese)](): Higher is better; unit: PERCENT. - [EM (English)](): Higher is better; unit: PERCENT. - [F1 (English)](): Higher is better; unit: PERCENT. - [Average EM](): Higher is better; unit: PERCENT. - [Average F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM (Swedish) | Result date | Report paper | | --- | --- | --- | --- | | HippoRAG2 | 47.4 | Not recorded | 69bcd4ae0636e5bf4afc2c39 | | DaPT | 46.5 | Not recorded | 69bcd4ae0636e5bf4afc2c39 | | Vanilla RAG | 23.6 | Not recorded | 69bcd4ae0636e5bf4afc2c39 | | Zero-shot | 22.5 | Not recorded | 69bcd4ae0636e5bf4afc2c39 | | GraphRAG | 22.3 | Not recorded | 69bcd4ae0636e5bf4afc2c39 | | CoT | 16.8 | Not recorded | 69bcd4ae0636e5bf4afc2c39 | ### HippoRAG2 EM (Swedish): 47.4. Result ID: 69bd20e347f34ce924a7f122. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"SA-Baselines"}. This record does not assert independent reproduction. ### DaPT EM (Swedish): 46.5. Result ID: 69bd20e347f34ce924a7f123. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Vanilla RAG EM (Swedish): 23.6. Result ID: 69bd20e347f34ce924a7f120. [Reporting paper]() Recorded evaluation configuration: {"Type":"SF-Baselines"}. This record does not assert independent reproduction. ### Zero-shot EM (Swedish): 22.5. Result ID: 69bd20e347f34ce924a7f11e. [Reporting paper]() Recorded evaluation configuration: {"Type":"SF-Baselines"}. This record does not assert independent reproduction. ### GraphRAG EM (Swedish): 22.3. Result ID: 69bd20e347f34ce924a7f121. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"SA-Baselines"}. This record does not assert independent reproduction. ### CoT EM (Swedish): 16.8. Result ID: 69bd20e347f34ce924a7f11f. [Reporting paper]() Recorded evaluation configuration: {"Type":"SF-Baselines"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.