{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2305.14160","title":"Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning","created":"2023-05-23","cited_by_count":236},{"id":"2307.03576","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention","created":"2023-07-07","cited_by_count":170},{"id":"2306.15063","title":"Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression","created":"2023-06-26","cited_by_count":146},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71},{"id":"1911.07176","title":"Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering","created":"2019-11-17","cited_by_count":59},{"id":"2401.12087","title":"Revisiting Demonstration Selection Strategies in In-Context Learning","created":"2024-01-22","cited_by_count":58},{"id":"2412.01003","title":"Competition Dynamics Shape Algorithmic Phases of In-Context Learning","created":"2024-12-01","cited_by_count":54},{"id":"2303.08119","title":"How Many Demonstrations Do You Need for In-context Learning?","created":"2023-03-14","cited_by_count":52},{"id":"2310.17086","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","created":"2023-10-26","cited_by_count":49},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46},{"id":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","cited_by_count":45},{"id":"2402.18819","title":"Dual Operating Modes of In-Context Learning","created":"2024-02-29","cited_by_count":43},{"id":"2305.15035","title":"Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations","created":"2023-05-24","cited_by_count":42},{"id":"2408.10147","title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers","created":"2024-08-19","cited_by_count":38},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35},{"id":"2311.00237","title":"The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis","created":"2023-11-01","cited_by_count":34},{"id":"2502.21212","title":"Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought","created":"2025-02-28","cited_by_count":32},{"id":"2411.02544","title":"Pretrained transformer efficiently learns low-dimensional target functions in-context","created":"2024-11-04","cited_by_count":31},{"id":"2402.14180","title":"Linear Transformers are Versatile In-Context Learners","created":"2024-02-21","cited_by_count":28},{"id":"2412.00104","title":"Differential learning kinetics govern the transition from memorization to generalization during in-context learning","created":"2024-11-27","cited_by_count":21},{"id":"2406.11233","title":"Probing the Decision Boundaries of In-context Learning in Large Language Models","created":"2024-06-17","cited_by_count":17},{"id":"2503.05631","title":"Strategy Coopetition Explains the Emergence and Transience of In-Context Learning","created":"2025-03-07","cited_by_count":17},{"id":"2506.05574","title":"When can in-context learning generalize out of task distribution?","created":"2025-06-05","cited_by_count":16},{"id":"2404.11225","title":"In-Context Learning State Vector with Inner and Momentum Optimization","created":"2024-04-17","cited_by_count":15},{"id":"2408.04532","title":"How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression","created":"2024-08-08","cited_by_count":14},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13},{"id":"2505.16225","title":"MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning","created":"2025-05-22","cited_by_count":13},{"id":"2406.01224","title":"Demonstration Augmentation for Zero-shot In-context Learning","created":"2024-06-03","cited_by_count":11},{"id":"2404.07546","title":"Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning","created":"2024-04-11","cited_by_count":8},{"id":"2412.03966","title":"Demonstration Selection for In-Context Learning via Reinforcement Learning","created":"2024-12-05","cited_by_count":8},{"id":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7},{"id":"2502.05164","title":"In-context denoising with one-layer transformers: connections between attention and associative memory retrieval","created":"2025-02-07","cited_by_count":7},{"id":"2404.00884","title":"Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models","created":"2024-04-01","cited_by_count":4},{"id":"2503.15579","title":"Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study","created":"2025-03-19","cited_by_count":4},{"id":"2202.00537","title":"Maximum Batch Frobenius Norm for Multi-Domain Text Classification","created":"2022-01-29","cited_by_count":3},{"id":"2406.00131","title":"From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When","created":"2024-05-31","cited_by_count":3},{"id":"2506.23149","title":"AlignEvoSkill: Towards Knowledge-Aware and Task-Aligned Agent Skill Evolution","created":"2025-06-29","cited_by_count":2},{"id":"2506.23146","title":"Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions","created":"2025-06-29","cited_by_count":1}],"next_cursor":null}