datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
SportsMetrics
SportsMetrics
Benchmark data to evaluate numerical reasoning and information fusion of LLMs.
SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Dong Yu, Fei Liu In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL'24), Bangkok, Thailand. Arxiv Paper
Usage
from datasets import load_dataset
def get_task(domain… See the full description on the dataset page: https://huggingface.co/datasets/huuuyeah/SportsMetrics.long_squad_v2
Dataset Card for long_squad_v2
long_squad_v2 is a long-context question answering dataset based on the SQuAD v2 format. It was constructed by concatenating multiple SQuAD v2 contexts to significantly increase the average document length, enabling training and evaluation of models on long-range understanding and sparse answer retrieval tasks.
Dataset Details
Uses
To load the dataset using the 🤗 Datasets library:
from datasets import load_dataset
dataset =… See the full description on the dataset page: https://huggingface.co/datasets/huutuan/long_squad_v2.ViFinQA
ViFinQA Dataset
Dataset Description
ViFinQA is a corpus-level dataset for Vietnamese financial question answering and numerical reasoning over annual financial statements. This public release contains 1,012 Vietnamese questions and 1,973 OCR-extracted reports from 100 Vietnamese listed companies, covering 2015–2025.
The dataset can support document retrieval, retrieval-augmented generation (RAG), financial information extraction, table understanding, and… See the full description on the dataset page: https://huggingface.co/datasets/HuuDong03uet/ViFinQA.Wu-kong
Wu-kong Dataset
This dataset provides a comprehensive knowledge base for the game "Black Myth: Wukong". It is derived from detailed game guides (including IGN's guide) and is structured to support Question Answering (QA) and Retrieval-Augmented Generation (RAG) tasks.
The dataset includes walkthroughs, boss strategies, item descriptions, and game mechanics explanations, making it an ideal resource for building game companion agents or testing RAG systems on domain-specific… See the full description on the dataset page: https://huggingface.co/datasets/huuuuuz/Wu-kong.SportsGenDataset and scripts for sports analyzing tasks proposed in research: When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Wenlin Yao, Hassan Foroosh, Dong Yu, Fei Liu Accepted to main conference of EMNLP 2024, Miami, Florida, USA Arxiv Paper
Abstract
Reasoning is most powerful when an LLM accurately aggregates relevant information. We examine the critical role of information aggregation in… See the full description on the dataset page: https://huggingface.co/datasets/huuuyeah/SportsGen.DeFineTest set and Data Resources for analogical reasoning with earnings call transcripts in research: DeFine: Decision-Making with Analogical Reasoning over Factor Profiles Yebowen Hu, Xiaoyang Wang, Wenlin Yao, Yiming Lu, Daoan Zhang, Hassan Foroosh, Dong Yu, Fei Liu Accepted to findings of ACL 2025, Vienna, Austria, USA 📄 Arxiv Paper
🏠 Home Page
🐙 Github
Abstract
LLMs are ideal for decision-making thanks to their ability to reason over long contexts. However, challenges… See the full description on the dataset page: https://huggingface.co/datasets/huuuyeah/DeFine.