{"list":"other","total":65,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"1912.05511","title":"Measurement and Fairness","created":"2019-12-11","cited_by_count":308},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184},{"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":"2309.14556","title":"Art or Artifice? Large Language Models and the False Promise of Creativity","created":"2023-09-25","cited_by_count":172},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104},{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2407.13248","title":"Are Large Language Models Capable of Generating Human-Level Narratives?","created":"2024-07-18","cited_by_count":79},{"id":"2404.16308","title":"WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models","created":"2024-04-25","cited_by_count":60},{"id":"2409.11360","title":"AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances","created":"2024-09-17","cited_by_count":60},{"id":"2301.09790","title":"The Next Chapter: A Study of Large Language Models in Storytelling","created":"2023-01-24","cited_by_count":58},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55},{"id":"2307.05543","title":"Typology of Risks of Generative Text-to-Image Models","created":"2023-07-08","cited_by_count":55},{"id":"2305.11844","title":"AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia","created":"2023-05-19","cited_by_count":54},{"id":"2403.06350","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","created":"2024-03-11","cited_by_count":52},{"id":"2205.07722","title":"How Different Groups Prioritize Ethical Values for Responsible AI","created":"2022-05-16","cited_by_count":49},{"id":"2501.00273","title":"Echoes in AI: Quantifying lack of plot diversity in LLM outputs","created":"2024-12-31","cited_by_count":48},{"id":"2305.11080","title":"Inspecting the Geographical Representativeness of Images from Text-to-Image Models","created":"2023-05-18","cited_by_count":44},{"id":"1808.06945","title":"A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation","created":"2018-08-21","cited_by_count":42},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40},{"id":"2311.09205","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","created":"2023-11-15","cited_by_count":32},{"id":"2310.07879","title":"Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Risks","created":"2023-10-11","cited_by_count":31},{"id":"2410.02677","title":"CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming","created":"2024-10-03","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":"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":"2401.17268","title":"Weaver: Foundation Models for Creative Writing","created":"2024-01-30","cited_by_count":27},{"id":"2407.01119","title":"Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?","created":"2024-07-01","cited_by_count":27},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25},{"id":"2307.10514","title":"Building Socio-culturally Inclusive Stereotype Resources with Community Engagement","created":"2023-07-20","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":"2502.14860","title":"ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning","created":"2025-02-20","cited_by_count":25},{"id":"2403.05696","title":"SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes","created":"2024-03-08","cited_by_count":24},{"id":"2403.14651","title":"DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures","created":"2024-02-23","cited_by_count":24},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24},{"id":"2403.05104","title":"How Culture Shapes What People Want From AI","created":"2024-03-08","cited_by_count":23},{"id":"2411.10939","title":"Evaluating Generative AI Systems is a Social Science Measurement Challenge","created":"2024-11-17","cited_by_count":23},{"id":"2309.08573","title":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","created":"2023-09-15","cited_by_count":18},{"id":"2503.19075","title":"The Case for \"Thick Evaluations\" of Cultural Representation in AI","created":"2025-03-24","cited_by_count":17},{"id":"2506.15355","title":"SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture","created":"2025-06-18","cited_by_count":16},{"id":"2510.06124","title":"Taxonomy of User Needs and Actions","created":"2025-10-07","cited_by_count":15},{"id":"2502.09870","title":"A Taxonomy of Linguistic Expressions That Contribute To Anthropomorphism of Language Technologies","created":"2025-02-14","cited_by_count":14},{"id":"2508.03712","title":"How Deep Is Representational Bias in LLMs? The Cases of Caste and Religion","created":"2025-07-22","cited_by_count":14},{"id":"2502.09642","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","created":"2025-02-10","cited_by_count":10},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10},{"id":"2406.12680","title":"Measuring Psychological Depth in Language Models","created":"2024-06-18","cited_by_count":9},{"id":"2411.07320","title":"Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations","created":"2024-11-11","cited_by_count":9},{"id":"2506.04851","title":"Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights","created":"2025-06-05","cited_by_count":8},{"id":"2408.00283","title":"Navigating Text-to-Image Generative Bias across Indic Languages","created":"2024-08-01","cited_by_count":5},{"id":"2410.19419","title":"KAHANI: Culturally-Nuanced Visual Storytelling Tool for Non-Western Cultures","created":"2024-10-25","cited_by_count":4},{"id":"2506.00784","title":"Research Borderlands: Analysing Writing Across Research Cultures","created":"2025-06-01","cited_by_count":3},{"id":"2407.17863","title":"factgenie: A Framework for Span-based Evaluation of Generated Texts","created":"2024-07-25","cited_by_count":2}],"next_cursor":null}