mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
feat(datasets): add MaritimeBench dataset and related configuration
Added MaritimeBench dataset, including dataset metadata, configuration files, data processing logic, and a text post-processing function. This dataset is designed to evaluate AI models' domain knowledge and reasoning ability in the maritime field.
This commit is contained in:
parent
6a6a1a5c0b
commit
8e6d2ab7e6
61
opencompass/configs/datasets/maritimebench/README.md
Normal file
61
opencompass/configs/datasets/maritimebench/README.md
Normal file
@ -0,0 +1,61 @@
|
|||||||
|
## 📘 About MaritimeBench
|
||||||
|
|
||||||
|
**MaritimeBench** 是航运行业首个基于“学科(一级)- 子学科(二级)- 具体考点(三级)”分类体系构建的专业知识评测集。该数据集包含 **1888 道客观选择题**,覆盖以下核心领域:
|
||||||
|
|
||||||
|
- 航海
|
||||||
|
- 轮机
|
||||||
|
- 电子电气员
|
||||||
|
- GMDSS(全球海上遇险与安全系统)
|
||||||
|
- 船员培训
|
||||||
|
|
||||||
|
评测内容涵盖理论知识、操作技能及行业规范,旨在:
|
||||||
|
|
||||||
|
- 提升 AI 模型在航运领域的 **理解与推理能力**
|
||||||
|
- 确保其在关键知识点上的 **准确性与适应性**
|
||||||
|
- 支持航运专业考试、船员培训及资质认证的 **自动化测评**
|
||||||
|
- 优化船舶管理、导航操作、海上通信等场景下的 **智能问答与决策系统**
|
||||||
|
|
||||||
|
MaritimeBench 基于行业权威标准,构建了 **系统、科学的知识评测体系**,全面衡量模型在航运各专业领域的表现,助力其专业化发展。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 🧪 示例
|
||||||
|
|
||||||
|
请回答单选题。要求只输出选项,不输出解释,将选项放在 `< >` 内,直接输出答案。
|
||||||
|
|
||||||
|
**题目 1:**
|
||||||
|
在船舶主推进动力装置中,传动轴系在运转中承受以下复杂的应力和负荷,但不包括______。
|
||||||
|
选项:
|
||||||
|
A. 电磁力
|
||||||
|
B. 压拉应力
|
||||||
|
C. 弯曲应力
|
||||||
|
D. 扭应力
|
||||||
|
**答:** `<A>`
|
||||||
|
|
||||||
|
**题目 2:**
|
||||||
|
当船舶实行 PMS 检验时,应将 CCS 现行规范中规定的特别检验纳入在 PMS 计划表中,下列应包括______。
|
||||||
|
① 每年应进行的确认性检查项目
|
||||||
|
② 每年应进行的拆检项目
|
||||||
|
③ 5 年内应拆检的项目
|
||||||
|
④ 5 年内应进行的确认性检查项目
|
||||||
|
选项:
|
||||||
|
A. ①④
|
||||||
|
B. ②④
|
||||||
|
C. ①③
|
||||||
|
D. ①②③④
|
||||||
|
**答:** `<C>`
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 📂 Dataset Links
|
||||||
|
|
||||||
|
- [MaritimeBench on Hugging Face](https://huggingface.co/datasets/Hi-Dolphin/MaritimeBench)
|
||||||
|
- [MaritimeBench on ModelScope](https://modelscope.cn/datasets/HiDolphin/MaritimeBench/summary)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 📊 模型测试结果
|
||||||
|
|
||||||
|
| dataset | version | metric | mode | Qwen2.5-32B |
|
||||||
|
|----- | ----- | ----- | ----- | -----|
|
||||||
|
| maritimebench | 6d56ec | accuracy | gen | 72.99 |
|
@ -0,0 +1,42 @@
|
|||||||
|
from opencompass.datasets import MaritimeBenchDataset
|
||||||
|
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
||||||
|
from opencompass.utils.text_postprocessors import parse_bracketed_answer
|
||||||
|
from opencompass.openicl.icl_evaluator import AccEvaluator
|
||||||
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
||||||
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
||||||
|
|
||||||
|
maritimebench_reader_cfg = dict(
|
||||||
|
input_columns=['question', 'A', 'B', 'C', 'D'],
|
||||||
|
output_column='answer',
|
||||||
|
train_split='test' # 明确指定使用test分割
|
||||||
|
)
|
||||||
|
|
||||||
|
maritimebench_infer_cfg = dict(
|
||||||
|
prompt_template=dict(
|
||||||
|
type=PromptTemplate,
|
||||||
|
template=dict(
|
||||||
|
round=[
|
||||||
|
dict(role='HUMAN', prompt='请回答单选题。要求只输出选项,不输出解释,将选项放在<>里,直接输出答案。示例:\n\n题目:在船舶主推进动力装置中,传动轴系在运转中承受以下复杂的应力和负荷,但不包括______。\n选项:\nA. 电磁力\nB. 压拉应力\nC. 弯曲应力\nD. 扭应力\n答:<A> 当前题目:\n {question}\nA:{A}\nB:{B}\nC:{C}\nD:{D}')
|
||||||
|
]
|
||||||
|
),
|
||||||
|
),
|
||||||
|
retriever=dict(type=ZeroRetriever), # 不使用上下文
|
||||||
|
inferencer=dict(type=GenInferencer) # 添加推理器配置
|
||||||
|
)
|
||||||
|
|
||||||
|
maritimebench_eval_cfg = dict(
|
||||||
|
evaluator=dict(type=AccEvaluator),
|
||||||
|
pred_postprocessor=dict(type=parse_bracketed_answer, options='A|B|C|D')
|
||||||
|
)
|
||||||
|
|
||||||
|
maritimebench_datasets = [
|
||||||
|
dict(
|
||||||
|
abbr='maritimebench',
|
||||||
|
type=MaritimeBenchDataset,
|
||||||
|
name='default',
|
||||||
|
path='opencompass/maritimebench',
|
||||||
|
reader_cfg=maritimebench_reader_cfg,
|
||||||
|
infer_cfg=maritimebench_infer_cfg,
|
||||||
|
eval_cfg=maritimebench_eval_cfg
|
||||||
|
)
|
||||||
|
]
|
@ -85,6 +85,7 @@ from .llm_compression import LLMCompressionDataset # noqa: F401, F403
|
|||||||
from .longbench import * # noqa: F401, F403
|
from .longbench import * # noqa: F401, F403
|
||||||
from .longbenchv2 import * # noqa: F401, F403
|
from .longbenchv2 import * # noqa: F401, F403
|
||||||
from .lveval import * # noqa: F401, F403
|
from .lveval import * # noqa: F401, F403
|
||||||
|
from .maritime_bench import * # noqa: F401, F403
|
||||||
from .mastermath2024v1 import * # noqa: F401, F403
|
from .mastermath2024v1 import * # noqa: F401, F403
|
||||||
from .math import * # noqa: F401, F403
|
from .math import * # noqa: F401, F403
|
||||||
from .math401 import * # noqa: F401, F403
|
from .math401 import * # noqa: F401, F403
|
||||||
|
64
opencompass/datasets/maritime_bench.py
Normal file
64
opencompass/datasets/maritime_bench.py
Normal file
@ -0,0 +1,64 @@
|
|||||||
|
import json
|
||||||
|
import os.path as osp
|
||||||
|
from os import environ
|
||||||
|
|
||||||
|
import datasets
|
||||||
|
from datasets import Dataset, DatasetDict
|
||||||
|
|
||||||
|
from opencompass.registry import LOAD_DATASET
|
||||||
|
from opencompass.utils import get_data_path
|
||||||
|
|
||||||
|
from .base import BaseDataset
|
||||||
|
|
||||||
|
|
||||||
|
@LOAD_DATASET.register_module()
|
||||||
|
class MaritimeBenchDataset(BaseDataset):
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def load(path: str, name: str) -> datasets.Dataset:
|
||||||
|
path = get_data_path(path)
|
||||||
|
dataset = DatasetDict()
|
||||||
|
dataset_list = []
|
||||||
|
|
||||||
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
||||||
|
from modelscope import MsDataset
|
||||||
|
for split in ['test']:
|
||||||
|
# 从 ModelScope 加载数据
|
||||||
|
ms_dataset = MsDataset.load(path,
|
||||||
|
subset_name=name,
|
||||||
|
split=split)
|
||||||
|
|
||||||
|
for line in ms_dataset:
|
||||||
|
question = line['question']
|
||||||
|
A = line['A']
|
||||||
|
B = line['B']
|
||||||
|
C = line['C']
|
||||||
|
D = line['D']
|
||||||
|
answer = line['answer']
|
||||||
|
dataset_list.append({
|
||||||
|
'question': question,
|
||||||
|
'A': A,
|
||||||
|
'B': B,
|
||||||
|
'C': C,
|
||||||
|
'D': D,
|
||||||
|
'answer': answer,
|
||||||
|
})
|
||||||
|
# dataset[split] = Dataset.from_list(dataset_list)
|
||||||
|
else:
|
||||||
|
for split in ['test']:
|
||||||
|
filename = osp.join(path, split, f'{name}_{split}.jsonl')
|
||||||
|
with open(filename, encoding='utf-8') as f:
|
||||||
|
for line in f:
|
||||||
|
data = json.loads(line)
|
||||||
|
dataset_list.append({
|
||||||
|
'question': data['question'],
|
||||||
|
'A': data['A'],
|
||||||
|
'B': data['B'],
|
||||||
|
'C': data['C'],
|
||||||
|
'D': data['D'],
|
||||||
|
'answer': data['answer']
|
||||||
|
})
|
||||||
|
|
||||||
|
dataset[split] = Dataset.from_list(dataset_list)
|
||||||
|
|
||||||
|
return dataset
|
@ -420,6 +420,11 @@ DATASETS_MAPPING = {
|
|||||||
"hf_id": "",
|
"hf_id": "",
|
||||||
"local": "./data/OlympiadBench",
|
"local": "./data/OlympiadBench",
|
||||||
},
|
},
|
||||||
|
"opencompass/maritimebench": {
|
||||||
|
"ms_id": "HiDolphin/MaritimeBench",
|
||||||
|
"hf_id": "Hi-Dolphin/MaritimeBench",
|
||||||
|
"local": "./data/maritimebench",
|
||||||
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
DATASETS_URL = {
|
DATASETS_URL = {
|
||||||
|
@ -283,3 +283,10 @@ def extract_non_reasoning_content(
|
|||||||
re.DOTALL)
|
re.DOTALL)
|
||||||
non_reasoning_content = reasoning_regex.sub('', text).strip()
|
non_reasoning_content = reasoning_regex.sub('', text).strip()
|
||||||
return non_reasoning_content
|
return non_reasoning_content
|
||||||
|
|
||||||
|
|
||||||
|
def parse_bracketed_answer(text: str, options: str) -> str:
|
||||||
|
match = re.search(rf'<({options})>', text)
|
||||||
|
if match:
|
||||||
|
return match.group(1)
|
||||||
|
return ''
|
Loading…
Reference in New Issue
Block a user