TransLaw Benchmark

What is TransLaw?

本文提出TransLaw——专为香港判例翻译设计的协同交互式多智能体框架。该框架创新性地将传统翻译流程拆解为翻译、错误标注及校对修正三大子任务，并分配三个智能体协同执行。为评估框架性能，我们构建了大规模双语基准数据集BJC…

Released

2025-07-01

Evaluates

语言, Language, 智能体, Agent, 指令跟随, Instruct, Legal AI, 任务执行, Task Execution, 语言理解, Comprehension, 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/TransLaw

TransLaw paper and dataset

• Paper https://arxiv.org/pdf/2507.00875
• Dataset https://huggingface.co/datasets/xxuan-nlp/CFA_Judgement_Corpus_97-22

Which sources cite TransLaw?

• TransLaw

Related 语言, Language, 智能体, Agent, 指令跟随, Instruct, Legal AI, 任务执行, Task Execution, 语言理解, Comprehension, 指令遵循, Instruction Following, 不支持, Unsupported benchmarks

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