IFIR Benchmark

What is IFIR?

IFIR is the first comprehensive benchmark designed to evaluate instruction-following information retrieval (IR) in expert domains. IFIR includes 2,426…

Released

2025-03-06

Evaluates

指令跟随, Instruct, 大语言模型, LLM, 指令遵循, Instruction Following, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

IFIR paper, code and dataset

• Paper https://arxiv.org/abs/2503.04644
• Code https://github.com/SighingSnow/IFIR
• Dataset https://huggingface.co/datasets/songtingyu/IFIR

Which sources cite IFIR?

• IFIR

Related 指令跟随, Instruct, 大语言模型, LLM, 指令遵循, Instruction Following, 不支持, Unsupported benchmarks

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