# CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset

arXiv: https://arxiv.org/abs/2507.22752 · HTML: https://mlsanity.com/paper/2507.22752/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 75 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Builds on (most cited first, 30 of 48)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models](https://mlsanity.com/paper/2306.05179/) (2023)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer](https://mlsanity.com/paper/2311.08526/) (2023)
- [INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge](https://mlsanity.com/paper/2411.19799/) (2024)
- [xGQA: Cross-Lingual Visual Question Answering](https://mlsanity.com/paper/2109.06082/) (2021)
- [Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform](https://mlsanity.com/paper/2110.05802/) (2021)
- [All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages](https://mlsanity.com/paper/2411.16508/) (2024)

## Built on by (most cited first, 4 of 4)

- [Charting the European LLM Benchmarking Landscape: A New Taxonomy and a Set of Best Practices](https://mlsanity.com/paper/2510.24450/) (2025)
- [Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation](https://mlsanity.com/paper/2608.07763/) (2026)
- [LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation](https://mlsanity.com/paper/2603.09403/) (2026)
- [Do LLMs Make More Mistakes If They Do Not Believe the Input Data?](https://mlsanity.com/paper/2609.09363/) (2026)

## Abstract (arXiv)

We introduce CUS-QA, a benchmark for evaluation of open-ended regional question answering that encompasses both textual and visual modalities. We also provide strong baselines using state-of-the-art large language models (LLMs). Our dataset consists of manually curated questions and answers grounded in Wikipedia, created by native speakers from Czechia, Slovakia, and Ukraine, with accompanying English translations. It includes both purely textual questions and those requiring visual understanding. We evaluate state-of-the-art LLMs through prompting and add human judgments of answer correctness. Using these human evaluations, we analyze the reliability of existing automatic evaluation metrics. Our baseline results show that even the best open-weight LLMs achieve only over 40% accuracy on textual questions and below 30% on visual questions. LLM-based evaluation metrics show strong correlation with human judgment, while traditional string-overlap metrics perform surprisingly well due to the prevalence of named entities in answers.