LaRA Benchmark

What is LaRA?

LaRA is a focused benchmark for testing Retrieval-Augmented Generation (RAG) and long-context LLMs. Benchmark Radar tracks LaRA, cited by 1 source documents…

Released

2025-02-14

Evaluates

长文本, Long-Context, 大语言模型, LLM, 长上下文, Long Context, 检索能力, Retrieval, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/LaRA

LaRA paper and code

• Paper https://arxiv.org/abs/2502.09977
• Code https://github.com/Alibaba-NLP/LaRA

Which sources cite LaRA?

• LaRA

Related 长文本, Long-Context, 大语言模型, LLM, 长上下文, Long Context, 检索能力, Retrieval, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard