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:
zhanghaoyu 2025-04-14 09:51:43 +08:00
parent 6a6a1a5c0b
commit 8e6d2ab7e6
6 changed files with 180 additions and 0 deletions

View 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 |

View File

@ -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
)
]

View File

@ -85,6 +85,7 @@ from .llm_compression import LLMCompressionDataset # noqa: F401, F403
from .longbench import * # noqa: F401, F403
from .longbenchv2 import * # noqa: F401, F403
from .lveval import * # noqa: F401, F403
from .maritime_bench import * # noqa: F401, F403
from .mastermath2024v1 import * # noqa: F401, F403
from .math import * # noqa: F401, F403
from .math401 import * # noqa: F401, F403

View 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

View File

@ -420,6 +420,11 @@ DATASETS_MAPPING = {
"hf_id": "",
"local": "./data/OlympiadBench",
},
"opencompass/maritimebench": {
"ms_id": "HiDolphin/MaritimeBench",
"hf_id": "Hi-Dolphin/MaritimeBench",
"local": "./data/maritimebench",
},
}
DATASETS_URL = {

View File

@ -283,3 +283,10 @@ def extract_non_reasoning_content(
re.DOTALL)
non_reasoning_content = reasoning_regex.sub('', text).strip()
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 ''