# Multilingual Table Question Answering on MultiTEND German Source: [Multilingual Table Question Answering on MultiTEND German]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:42.500Z Evaluation of Multilingual Table Question Answering performance on the German subset of the MultiTEND dataset, reporting metrics including EM, QSM, QFC, EX, EFM, and EVM. 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 Table Question Answering | | Dataset (including any stated split) | MultiTEND German | | Metric | EM (Exact Match) | | 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 (Exact Match)](): Higher is better; unit: PERCENT. - [QSM (Query Structure Match)](): Higher is better; unit: PERCENT. - [QFC (Query Form Consistency)](): Higher is better; unit: PERCENT. - [EX (Execution Accuracy)](): Higher is better; unit: PERCENT. - [EFM (Execution Form Match)](): Higher is better; unit: PERCENT. - [EVM (Execution Value Match)](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM (Exact Match) | Result date | Report paper | | --- | --- | --- | --- | | MultiLink | 25.65 | Not recorded | 68fa76fd1e209131cea70476 | | SMART | 18.3 | Not recorded | 68fa76fd1e209131cea70476 | | Fine-tuned Llama | 15.78 | Not recorded | 68fa76fd1e209131cea70476 | | RAG for LLM | 14.33 | Not recorded | 68fa76fd1e209131cea70476 | | Few-shot LLM | 10.65 | Not recorded | 68fa76fd1e209131cea70476 | | Zero-shot LLM | 0.54 | Not recorded | 68fa76fd1e209131cea70476 | ### MultiLink EM (Exact Match): 25.65. Result ID: 699468623a6c3148491d095d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SMART EM (Exact Match): 18.3. Result ID: 699468623a6c3148491d095c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Fine-tuned Llama EM (Exact Match): 15.78. Result ID: 699468623a6c3148491d0958. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction. ### RAG for LLM EM (Exact Match): 14.33. Result ID: 699468623a6c3148491d095b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"RAG"}. This record does not assert independent reproduction. ### Few-shot LLM EM (Exact Match): 10.65. Result ID: 699468623a6c3148491d095a. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Few-shot"}. This record does not assert independent reproduction. ### Zero-shot LLM EM (Exact Match): 0.54. Result ID: 699468623a6c3148491d0959. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.