{"total":46,"rows":[{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"area":null},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","cited_by_count":30,"area":null},{"id":"2411.06032","title":"LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output","created":"2024-11-09","cited_by_count":27,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2503.10688","title":"CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding","created":"2025-03-12","cited_by_count":14,"area":null},{"id":"2510.05931","title":"Hire Your Anthropologist! Rethinking Culture Benchmarks Through an Anthropological Lens","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2505.21693","title":"MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2509.19274","title":"DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture","created":"2025-09-23","cited_by_count":13,"area":null},{"id":"2509.16188","title":"CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs","created":"2025-09-19","cited_by_count":12,"area":null},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2502.14865","title":"Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts","created":"2025-02-20","cited_by_count":11,"area":null},{"id":"2408.13534","title":"Cultural Adaptation of Menus: A Fine-Grained Approach","created":"2024-08-24","cited_by_count":8,"area":null},{"id":"2503.17485","title":"SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia","created":"2025-03-21","cited_by_count":8,"area":null},{"id":"2601.13024","title":"Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2506.01565","title":"Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2510.06371","title":"OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2410.19419","title":"KAHANI: Culturally-Nuanced Visual Storytelling Tool for Non-Western Cultures","created":"2024-10-25","cited_by_count":4,"area":null},{"id":"2411.14647","title":"Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains","created":"2024-11-22","cited_by_count":4,"area":null},{"id":"2412.20541","title":"SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes","created":"2024-12-29","cited_by_count":4,"area":null},{"id":"2505.24456","title":"CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2507.22752","title":"CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2508.02241","title":"Isolating Culture Neurons in Multilingual Large Language Models","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2510.20042","title":"Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2510.01247","title":"Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sports","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2603.21165","title":"Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2507.03330","title":"Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2601.05699","title":"Afri-MCQA: Multimodal Cultural Question Answering for African Languages","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2603.01211","title":"A Unified Framework to Quantify Cultural Intelligence of AI","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2608.27135","title":"Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2502.07455","title":"RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation","created":"2025-02-11","cited_by_count":1,"area":null},{"id":"2604.06484","title":"ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMs","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.20676","title":"Jury Duty: Calibration and Orientation Failures in MLLM-as-a-Judge Under Cultural Ambiguity","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.01942","title":"CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2609.11532","title":"Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2510.26861","title":"Evaluating Perspectival Biases in Cross-Modal Retrieval","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2603.22249","title":"EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.23521","title":"Chitrakshara: A Large Multilingual Multimodal Dataset for Indian languages","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.26013","title":"Toward Culturally Grounded Natural Language Processing","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2606.03345","title":"Beyond Semantics: Modeling Factual and Affective Perceptual Experiences from Vision-Language Data","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.07311","title":"CultureScore: Evaluating Cultural Faithfulness in Video Generation Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.08034","title":"Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2608.09316","title":"MemeMind: Reference-Guided Trace Construction for Offline Context Optimization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.21853","title":"PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.30475","title":"ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25298","title":"FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}