{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2411.10109","title":"LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals","created":"2024-11-15","cited_by_count":249},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"2311.04076","title":"Do LLMs exhibit human-like response biases? A case study in survey design","created":"2023-11-07","cited_by_count":180},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169},{"id":"2010.03532","title":"What Can We Learn from Collective Human Opinions on Natural Language Inference Data?","created":"2020-10-07","cited_by_count":153},{"id":"2402.01908","title":"Large language models that replace human participants can harmfully misportray and flatten identity groups","created":"2024-02-02","cited_by_count":144},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115},{"id":"2310.15819","title":"Generative Language Models Exhibit Social Identity Biases","created":"2023-10-24","cited_by_count":111},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109},{"id":"2406.11657","title":"Can LLM be a Personalized Judge?","created":"2024-06-17","cited_by_count":100},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97},{"id":"2306.11247","title":"DICES Dataset: Diversity in Conversational AI Evaluation for Safety","created":"2023-06-20","cited_by_count":86},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50},{"id":"2302.07267","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","created":"2023-02-13","cited_by_count":45},{"id":"2410.20268","title":"Centaur: a foundation model of human cognition","created":"2024-10-26","cited_by_count":36},{"id":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25},{"id":"2404.00750","title":"Can Language Models Recognize Convincing Arguments?","created":"2024-03-31","cited_by_count":21},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19},{"id":"2502.16940","title":"Reasoning Does Not Necessarily Improve Role-Playing Ability","created":"2025-02-24","cited_by_count":14},{"id":"2503.02250","title":"AI Automatons: AI Systems Intended to Imitate Humans","created":"2025-03-04","cited_by_count":10},{"id":"2502.19158","title":"When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning","created":"2025-02-26","cited_by_count":9},{"id":"2409.17990","title":"Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models","created":"2024-09-26","cited_by_count":4},{"id":"2503.03335","title":"iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News","created":"2025-03-05","cited_by_count":4}],"next_cursor":null}