{"list":"other","total":90,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"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":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2009.03393","title":"Generative Language Modeling for Automated Theorem Proving","created":"2020-09-07","cited_by_count":388},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226},{"id":"2212.10001","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","created":"2022-12-20","cited_by_count":222},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2506.20670","title":"MMSearch-R1: Incentivizing LMMs to Search","created":"2025-06-25","cited_by_count":124},{"id":"2401.03729","title":"The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance","created":"2024-01-08","cited_by_count":100},{"id":"2405.18357","title":"Faithful Logical Reasoning via Symbolic Chain-of-Thought","created":"2024-05-28","cited_by_count":100},{"id":"2406.04271","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","created":"2024-06-06","cited_by_count":91},{"id":"2208.02957","title":"Meaning without reference in large language models","created":"2022-08-05","cited_by_count":76},{"id":"2305.19234","title":"Grammar Prompting for Domain-Specific Language Generation with Large Language Models","created":"2023-05-30","cited_by_count":58},{"id":"2501.05952","title":"Scalable Vision Language Model Training via High Quality Data Curation","created":"2025-01-10","cited_by_count":55},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54},{"id":"2405.21047","title":"Grammar-Aligned Decoding","created":"2024-05-31","cited_by_count":54},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52},{"id":"2406.11271","title":"MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens","created":"2024-06-17","cited_by_count":50},{"id":"2512.17260","title":"Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience","created":"2025-12-19","cited_by_count":44},{"id":"2311.09278","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","created":"2023-11-15","cited_by_count":39},{"id":"2406.10248","title":"On the Worst Prompt Performance of Large Language Models","created":"2024-06-08","cited_by_count":38},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36},{"id":"2507.15225","title":"Solving Formal Math Problems by Decomposition and Iterative Reflection","created":"2025-07-21","cited_by_count":35},{"id":"2510.15511","title":"Language Models are Injective and Hence Invertible","created":"2025-10-17","cited_by_count":35},{"id":"2511.22659","title":"Geometrically-Constrained Agent for Spatial Reasoning","created":"2025-11-27","cited_by_count":26},{"id":"2601.01984","title":"Thinking with Blueprints: Assisting Vision-Language Models in Spatial Reasoning via Structured Object Representation","created":"2026-01-05","cited_by_count":21},{"id":"2404.02575","title":"Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models","created":"2024-04-03","cited_by_count":20},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18},{"id":"2511.12869","title":"On the Fundamental Limits of LLMs at Scale","created":"2025-11-17","cited_by_count":18},{"id":"2404.07751","title":"Generating consistent PDDL domains with Large Language Models","created":"2024-04-11","cited_by_count":15},{"id":"2503.00870","title":"NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains","created":"2025-03-02","cited_by_count":15},{"id":"2307.01201","title":"Schema-learning and rebinding as mechanisms of in-context learning and emergence","created":"2023-06-16","cited_by_count":14},{"id":"2507.05118","title":"VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots","created":"2025-07-07","cited_by_count":14},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13},{"id":"2510.21302","title":"Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning","created":"2025-10-24","cited_by_count":11},{"id":"2501.00830","title":"LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actions","created":"2025-01-01","cited_by_count":10},{"id":"2510.19546","title":"Conditions for Catastrophic Forgetting in Multilingual Translation","created":"2025-10-22","cited_by_count":10},{"id":"2501.00958","title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","created":"2025-01-01","cited_by_count":9},{"id":"2506.21230","title":"World-aware Planning Narratives Enhance Large Vision-Language Model Planner","created":"2025-06-26","cited_by_count":9},{"id":"2506.17104","title":"Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving","created":"2025-06-20","cited_by_count":8},{"id":"2604.22709","title":"Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought","created":"2026-04-24","cited_by_count":8},{"id":"2310.00313","title":"Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models","created":"2023-09-30","cited_by_count":7},{"id":"2508.10003","title":"Semantic Structure in Large Language Model Embeddings","created":"2025-08-04","cited_by_count":7},{"id":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6},{"id":"2510.19429","title":"NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning","created":"2025-10-22","cited_by_count":5},{"id":"2604.13346","title":"AgentSPEX: An Agent SPecification and EXecution Language","created":"2026-04-14","cited_by_count":5},{"id":"2506.16151","title":"Under the Shadow of Babel: How Language Shapes Reasoning in LLMs","created":"2025-06-19","cited_by_count":4},{"id":"2510.13905","title":"Schema for In-Context Learning","created":"2025-10-14","cited_by_count":4},{"id":"2502.01657","title":"Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations","created":"2025-01-31","cited_by_count":3},{"id":"2502.09589","title":"Logical forms complement probability in understanding language model (and human) performance","created":"2025-02-13","cited_by_count":3},{"id":"2509.05540","title":"Combining TSL and LLM to Automate REST API Testing: A Comparative Study","created":"2025-09-05","cited_by_count":3},{"id":"2412.06107","title":"Infusing Prompts with Syntax and Semantics","created":"2024-12-08","cited_by_count":2}],"next_cursor":null}