{"list":"other","total":55,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199},{"id":"2412.03304","title":"Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation","created":"2024-12-04","cited_by_count":191},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153},{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129},{"id":"2406.05967","title":"CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark","created":"2024-06-10","cited_by_count":120},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"2402.09369","title":"Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking","created":"2024-02-14","cited_by_count":63},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60},{"id":"2404.12464","title":"NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models","created":"2024-04-18","cited_by_count":48},{"id":"2110.00672","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","created":"2021-10-01","cited_by_count":39},{"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},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","cited_by_count":36},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34},{"id":"2406.12232","title":"\"You Gotta be a Doctor, Lin\": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations","created":"2024-06-18","cited_by_count":33},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31},{"id":"2205.12247","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","created":"2022-05-24","cited_by_count":30},{"id":"2404.06833","title":"Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge","created":"2024-04-10","cited_by_count":29},{"id":"2305.11262","title":"CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models","created":"2023-05-18","cited_by_count":28},{"id":"2404.06664","title":"CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge","created":"2024-04-10","cited_by_count":28},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25},{"id":"2406.10486","title":"Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?","created":"2024-06-15","cited_by_count":25},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25},{"id":"2505.15229","title":"Multilingual Prompting for Improving LLM Generation Diversity","created":"2025-05-21","cited_by_count":25},{"id":"2305.13198","title":"Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale","created":"2023-05-22","cited_by_count":24},{"id":"2403.05696","title":"SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes","created":"2024-03-08","cited_by_count":24},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23},{"id":"2501.04662","title":"On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena","created":"2025-01-08","cited_by_count":22},{"id":"2502.11995","title":"Presumed Cultural Identity: How Names Shape LLM Responses","created":"2025-02-17","cited_by_count":21},{"id":"2508.04796","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","created":"2025-08-06","cited_by_count":20},{"id":"2306.05076","title":"DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models","created":"2023-06-08","cited_by_count":17},{"id":"2503.19075","title":"The Case for \"Thick Evaluations\" of Cultural Representation in AI","created":"2025-03-24","cited_by_count":17},{"id":"2503.00151","title":"Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs","created":"2025-02-28","cited_by_count":15},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15},{"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},{"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},{"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},{"id":"2501.01056","title":"Risks of Cultural Erasure in Large Language Models","created":"2025-01-02","cited_by_count":9},{"id":"2412.20760","title":"Attributing Culture-Conditioned Generations to Pretraining Corpora","created":"2024-12-30","cited_by_count":8},{"id":"2406.02050","title":"JBBQ: Japanese Bias Benchmark for Analyzing Social Biases in Large Language Models","created":"2024-06-04","cited_by_count":7},{"id":"2506.00068","title":"Framing Political Bias in Multilingual LLMs Across Pakistani Languages","created":"2025-05-29","cited_by_count":5},{"id":"2502.18583","title":"What are Foundation Models Cooking in the Post-Soviet World?","created":"2025-02-25","cited_by_count":3},{"id":"2507.02088","title":"McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models","created":"2025-07-02","cited_by_count":3},{"id":"2505.18466","title":"Purdah and Patriarchy: Evaluating and Mitigating South Asian Biases in Open-Ended Multilingual LLM Generations","created":"2025-05-24","cited_by_count":2}],"next_cursor":null}