{"list":"other","total":52,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2305.03495","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","created":"2023-05-04","cited_by_count":653},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"1904.07272","title":"Introduction to Multi-Armed Bandits","created":"2019-04-15","cited_by_count":481},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2402.02057","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding","created":"2024-02-03","cited_by_count":298},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","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":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"2012.09823","title":"Continual Lifelong Learning in Natural Language Processing: A Survey","created":"2020-12-17","cited_by_count":152},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"2406.16937","title":"A Complete Survey on LLM-based AI Chatbots","created":"2024-06-17","cited_by_count":71},{"id":"2305.11840","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","created":"2023-05-19","cited_by_count":66},{"id":"2310.07251","title":"Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs","created":"2023-10-11","cited_by_count":64},{"id":"2409.11360","title":"AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances","created":"2024-09-17","cited_by_count":60},{"id":"1904.02743","title":"How should my chatbot interact? A survey on human-chatbot interaction design","created":"2019-04-04","cited_by_count":56},{"id":"2404.10199","title":"CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting","created":"2024-04-16","cited_by_count":55},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53},{"id":"2406.14805","title":"How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions","created":"2024-06-21","cited_by_count":52},{"id":"2307.07870","title":"Large Language Models as Superpositions of Cultural Perspectives","created":"2023-07-15","cited_by_count":49},{"id":"2404.18460","title":"Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in","created":"2024-04-29","cited_by_count":46},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40},{"id":"2011.13464","title":"Meta-learning in natural and artificial intelligence","created":"2020-11-26","cited_by_count":39},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39},{"id":"2310.05280","title":"Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems","created":"2023-10-08","cited_by_count":37},{"id":"2402.17302","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","created":"2024-02-27","cited_by_count":36},{"id":"2311.01012","title":"COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances","created":"2023-11-02","cited_by_count":35},{"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":"2406.01285","title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","created":"2024-06-03","cited_by_count":26},{"id":"2309.13356","title":"Probing the Moral Development of Large Language Models through Defining Issues Test","created":"2023-09-23","cited_by_count":25},{"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":"2403.14651","title":"DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures","created":"2024-02-23","cited_by_count":24},{"id":"2311.16421","title":"CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models","created":"2023-11-28","cited_by_count":23},{"id":"2406.11661","title":"Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting","created":"2024-06-17","cited_by_count":22},{"id":"2407.09241","title":"The Sociolinguistic Foundations of Language Modeling","created":"2024-07-12","cited_by_count":13},{"id":"2403.09362","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","created":"2024-03-14","cited_by_count":10},{"id":"2310.19567","title":"CreoleVal: Multilingual Multitask Benchmarks for Creoles","created":"2023-10-30","cited_by_count":9},{"id":"2410.01811","title":"Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English","created":"2024-09-14","cited_by_count":8},{"id":"2408.02143","title":"Analyzing Cultural Representations of Emotions in LLMs through Mixed Emotion Survey","created":"2024-08-04","cited_by_count":7},{"id":"2409.15380","title":"Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipino","created":"2024-09-20","cited_by_count":3},{"id":"2009.10750","title":"Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job","created":"2020-09-22","cited_by_count":2}],"next_cursor":null}