# LongBench: A Multilingual, Multitask Benchmark Tailored for Long Context Understanding
# LongBench: A Multilingual, Multitask Benchmark for Long Context Understanding
**LongBench** is the first benchmark for multilingual, multitask, and comprehensive assessment of **long context understanding** capabilities of large language models. LongBench includes different languages (Chinese and English) to provide a more comprehensive evaluation of the large models' multilingual capabilities on long contexts. In addition, LongBench consists of 20 different tasks, covering key long context application scenarios such as single-document QA, multi-document QA, summarization, few-shot learning, code completion, and synthetic tasks.
**LongBench** is the first benchmark for multilingual, multitask, and comprehensive assessment of **long context understanding** capabilities of large language models. LongBench includes different languages (Chinese and English) to provide a more comprehensive evaluation of the large models' multilingual capabilities on long contexts. In addition, LongBench consists of 20 different tasks, covering key long context application scenarios such as single-document QA, multi-document QA, summarization, few-shot learning, code completion, and synthetic tasks.
...
@@ -191,4 +191,4 @@ The following tables show the Zero-shot evaluation results (%) on all datasets,
...
@@ -191,4 +191,4 @@ The following tables show the Zero-shot evaluation results (%) on all datasets,
## Citation
## Citation
This is a joint work by **THU-KEG** and **Zhipu AI**. We are currently working on the paper, and the citation information will be updated when it's ready. Please stay tuned~
This is a joint work by **THU-KEG** and **Zhipu AI**. We are currently working on the paper, and the citation information will be updated when it's ready. Please stay tuned~
When citing our work, please cite all of the original dataset papers. The relevant citation information is listed [here](refs/ref.bib).
When citing our work, please cite all of the original dataset papers. The relevant citation information is listed [here](refs/ref.bib).
