{"total":120,"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":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101,"area":"mllm"},{"id":"2410.16153","title":"Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages","created":"2024-10-21","cited_by_count":64,"area":"mllm"},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64,"area":"mllm"},{"id":"2410.17385","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","created":"2024-10-22","cited_by_count":59,"area":"mllm"},{"id":"2411.16508","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","created":"2024-11-25","cited_by_count":55,"area":"wm"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2501.01282","title":"CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries","created":"2025-01-02","cited_by_count":42,"area":"mllm"},{"id":"2410.12705","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","created":"2024-10-16","cited_by_count":39,"area":"mllm"},{"id":"2504.04633","title":"M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering","created":"2025-04-06","cited_by_count":35,"area":"mllm"},{"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":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2410.17250","title":"JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation","created":"2024-10-22","cited_by_count":19,"area":"mllm"},{"id":"2505.11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","created":"2025-05-16","cited_by_count":19,"area":"mllm"},{"id":"2406.11665","title":"See It from My Perspective: How Language Affects Cultural Bias in Image Understanding","created":"2024-06-17","cited_by_count":17,"area":"mllm"},{"id":"2410.18976","title":"CAMEL-Bench: A Comprehensive Arabic LMM Benchmark","created":"2024-10-24","cited_by_count":17,"area":"lr"},{"id":"2506.03922","title":"HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models","created":"2025-06-04","cited_by_count":17,"area":"mllm"},{"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":"2506.15355","title":"SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture","created":"2025-06-18","cited_by_count":16,"area":null},{"id":"2505.17670","title":"Towards General Continuous Memory for Vision-Language Models","created":"2025-05-23","cited_by_count":15,"area":"mllm"},{"id":"2502.08914","title":"Diffusion Models Through a Global Lens: Are They Culturally Inclusive?","created":"2025-02-13","cited_by_count":14,"area":"diffusion"},{"id":"2502.14906","title":"Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2508.07493","title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding","created":"2025-08-10","cited_by_count":14,"area":"rag"},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","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":"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":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2505.14462","title":"RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2512.11437","title":"CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare","created":"2025-12-12","cited_by_count":9,"area":null},{"id":"2407.01081","title":"CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation","created":"2024-07-01","cited_by_count":8,"area":"mllm"},{"id":"2407.06177","title":"Vision-Language Models under Cultural and Inclusive Considerations","created":"2024-07-08","cited_by_count":8,"area":"mllm"},{"id":"2505.14972","title":"Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies","created":"2025-05-20","cited_by_count":8,"area":"mllm"},{"id":"2506.08071","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2511.04727","title":"IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs","created":"2025-11-06","cited_by_count":8,"area":"mllm"},{"id":"2502.15972","title":"When Cultures Meet: Multicultural Text-to-Image Generation","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2503.21910","title":"JEEM: Vision-Language Understanding in Four Arabic Dialects","created":"2025-03-27","cited_by_count":7,"area":"mllm"},{"id":"2409.18023","title":"DARE: Diverse Visual Question Answering with Robustness Evaluation","created":"2024-09-26","cited_by_count":6,"area":"mllm"},{"id":"2505.21979","title":"Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset","created":"2025-05-28","cited_by_count":6,"area":"mllm"},{"id":"2601.11778","title":"Translation as a Scalable Proxy for Multilingual Evaluation","created":"2026-01-16","cited_by_count":6,"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":"2410.14991","title":"ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla","created":"2024-10-19","cited_by_count":5,"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":"2506.07032","title":"A Culturally-diverse Multilingual Multimodal Video Benchmark & Model","created":"2025-06-08","cited_by_count":5,"area":"mllm"},{"id":"2509.02949","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","created":"2025-09-03","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":"2502.17710","title":"Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2505.11275","title":"TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs","created":"2025-05-16","cited_by_count":4,"area":"mllm"},{"id":"2505.24456","title":"CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation","created":"2025-05-30","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":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2501.05122","title":"Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model","created":"2025-01-09","cited_by_count":3,"area":"mllm"},{"id":"2505.08910","title":"Behind Maya: Building a Multilingual Vision Language Model","created":"2025-05-13","cited_by_count":3,"area":"mllm"},{"id":"2505.15075","title":"Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs","created":"2025-05-21","cited_by_count":3,"area":"mllm"},{"id":"2505.22793","title":"Evaluation of Cultural Competence of Vision-Language Models","created":"2025-05-28","cited_by_count":3,"area":"mllm"},{"id":"2507.11939","title":"POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering","created":"2025-07-16","cited_by_count":3,"area":"mllm"},{"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":"2510.24942","title":"Finding Culture-Sensitive Neurons in Vision-Language Models","created":"2025-10-28","cited_by_count":3,"area":"mllm"},{"id":"2511.17004","title":"Vision Language Models are Confused Tourists","created":"2025-11-21","cited_by_count":3,"area":"mllm"},{"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":"2604.00909","title":"JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation","created":"2026-04-01","cited_by_count":3,"area":"mllm"},{"id":"2504.11108","title":"Benchmarking Vision Language Models on German Factual Data","created":"2025-04-15","cited_by_count":2,"area":"mllm"},{"id":"2507.11882","title":"Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2510.05291","title":"Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.09316","title":"A Survey of LLM Prompt Datasets: Taxonomy, Linguistic Patterns, and Practical Uses","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2512.01077","title":"ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2512.01419","title":"Rice-VL: Evaluating Vision-Language Models for Cultural Understanding Across ASEAN Countries","created":"2025-12-01","cited_by_count":2,"area":"mllm"},{"id":"2601.05699","title":"Afri-MCQA: Multimodal Cultural Question Answering for African Languages","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2602.05437","title":"Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2505.11876","title":"EAMET: Robust Massive Model Editing via Embedding Alignment Optimization","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2505.16566","title":"ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2506.12936","title":"CliniDial: A Naturally Occurring Multimodal Dialogue Dataset for Team Reflection in Action During Clinical Operation","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2507.20077","title":"The Devil is in the EOS: Sequence Training for Detailed Image Captioning","created":"2025-07-26","cited_by_count":1,"area":"mllm"},{"id":"2508.16762","title":"Toward Socially Aware Vision-Language Models: Evaluating Cultural Competence Through Multimodal Story Generation","created":"2025-08-22","cited_by_count":1,"area":"mllm"},{"id":"2509.22123","title":"Multilingual Vision-Language Models, A Survey","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2510.01963","title":"Bias beyond Borders: Global Inequalities in AI-Generated Music","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2512.05959","title":"M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG","created":"2025-12-05","cited_by_count":1,"area":"mllm"},{"id":"2512.17394","title":"Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?","created":"2025-12-19","cited_by_count":1,"area":"lr"},{"id":"2603.10814","title":"HanMoVLM: Large Vision-Language Models for Professional Artistic Painting Evaluation","created":"2026-03-11","cited_by_count":1,"area":"mllm"},{"id":"2605.12960","title":"DiM\\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging","created":"2026-05-13","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":"2607.04683","title":"Failing to See or Failing to Know? Attributing Errors in Vision-Language Models","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2608.07763","title":"Jako Tako or Fluent? Presenting PoVisLE: A Polish Vision-Language Evaluation","created":"2026-08-07","cited_by_count":1,"area":"mllm"},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2504.05995","title":"NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2508.05502","title":"MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs","created":"2025-08-07","cited_by_count":0,"area":"mllm"},{"id":"2509.26167","title":"'Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.16198","title":"EgMM-Corpus: A Multimodal Vision-Language Dataset for Egyptian Culture","created":"2025-10-17","cited_by_count":0,"area":"mllm"},{"id":"2510.26861","title":"Evaluating Perspectival Biases in Cross-Modal Retrieval","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.15183","title":"HinTel-AlignBench: A Framework and Benchmark for Hindi-Telugu with English-Aligned Samples","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.03400","title":"Eye-Q: A Multilingual Benchmark for Visual Word Puzzle Solving and Image-to-Phrase Reasoning","created":"2026-01-06","cited_by_count":0,"area":"lr"},{"id":"2602.02510","title":"Beyond Translation: Cross-Cultural Meme Transcreation with Vision-Language Models","created":"2026-01-23","cited_by_count":0,"area":"mllm"},{"id":"2602.02774","title":"AmharicStoryQA: A Multicultural Story Question Answering Benchmark in Amharic","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.10732","title":"Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling","created":"2026-02-11","cited_by_count":0,"area":"lr"},{"id":"2602.18729","title":"MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment","created":"2026-02-21","cited_by_count":0,"area":"mllm"},{"id":"2603.08275","title":"AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.26742","title":"Do Multilingual VLMs Reason Equally? A Cross-Lingual Visual Reasoning Audit for Indian Languages","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2604.02048","title":"Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models","created":"2026-04-02","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}