{"list":"other","total":63,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"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":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"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":"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":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"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":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2208.04024","title":"Social Simulacra: Creating Populated Prototypes for Social Computing Systems","created":"2022-08-08","cited_by_count":301},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140},{"id":"2411.11581","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","created":"2024-11-18","cited_by_count":132},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82},{"id":"2306.07951","title":"Questioning the Survey Responses of Large Language Models","created":"2023-06-13","cited_by_count":74},{"id":"2310.15100","title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","created":"2023-10-23","cited_by_count":70},{"id":"2502.16761","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","created":"2025-02-24","cited_by_count":66},{"id":"2406.17055","title":"Large Language Models Assume People are More Rational than We Really are","created":"2024-06-24","cited_by_count":54},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52},{"id":"2305.09620","title":"AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction","created":"2023-05-16","cited_by_count":48},{"id":"2408.02784","title":"LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory","created":"2024-08-05","cited_by_count":47},{"id":"2302.07267","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","created":"2023-02-13","cited_by_count":45},{"id":"2306.10062","title":"Revealing the structure of language model capabilities","created":"2023-06-14","cited_by_count":40},{"id":"2406.04391","title":"Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?","created":"2024-06-06","cited_by_count":40},{"id":"2509.05830","title":"Finetuning LLMs for Human Behavior Prediction in Social Science Experiments","created":"2025-09-06","cited_by_count":39},{"id":"2412.04403","title":"Establishing Task Scaling Laws via Compute-Efficient Model Ladders","created":"2024-12-05","cited_by_count":35},{"id":"2405.07248","title":"Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysis","created":"2024-05-12","cited_by_count":31},{"id":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29},{"id":"2601.14525","title":"Towards Execution-Grounded Automated AI Research","created":"2026-01-20","cited_by_count":28},{"id":"2310.11616","title":"Evidence of interrelated cognitive-like capabilities in large language models: Indications of artificial general intelligence or achievement?","created":"2023-10-17","cited_by_count":27},{"id":"2304.01420","title":"Scientists' Perspectives on the Potential for Generative AI in their Fields","created":"2023-04-04","cited_by_count":22},{"id":"2410.07362","title":"Large Language Models in Qualitative Research: Uses, Tensions, and Intentions","created":"2024-10-09","cited_by_count":21},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20},{"id":"2510.06084","title":"Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability","created":"2025-10-07","cited_by_count":20},{"id":"2306.09928","title":"Friend or Foe? Exploring the Implications of Large Language Models on the Science System","created":"2023-06-16","cited_by_count":16},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12},{"id":"2505.07457","title":"Can Generative AI agents behave like humans? Evidence from laboratory market experiments","created":"2025-05-12","cited_by_count":10},{"id":"2501.06834","title":"LLMs Model Non-WEIRD Populations: Experiments with Synthetic Cultural Agents","created":"2025-01-12","cited_by_count":6},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6},{"id":"2409.02391","title":"Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Translation","created":"2024-09-04","cited_by_count":5},{"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}],"next_cursor":null}