{"total":59,"rows":[{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721,"area":null},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185,"area":null},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133,"area":null},{"id":"2405.00200","title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","created":"2024-04-30","cited_by_count":128,"area":null},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84,"area":null},{"id":"2212.10947","title":"Parallel Context Windows for Large Language Models","created":"2022-12-21","cited_by_count":81,"area":null},{"id":"2406.15765","title":"Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration","created":"2024-06-22","cited_by_count":74,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2407.01100","title":"Eliminating Position Bias of Language Models: A Mechanistic Approach","created":"2024-07-01","cited_by_count":65,"area":null},{"id":"2307.07164","title":"Learning to Retrieve In-Context Examples for Large Language Models","created":"2023-07-14","cited_by_count":60,"area":null},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2405.16156","title":"Mixture of In-Context Prompters for Tabular PFNs","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32,"area":null},{"id":"2401.07364","title":"PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws","created":"2024-01-14","cited_by_count":31,"area":null},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2402.13449","title":"CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory","created":"2024-02-21","cited_by_count":24,"area":null},{"id":"2306.14101","title":"Language models are weak learners","created":"2023-06-25","cited_by_count":22,"area":null},{"id":"2305.11170","title":"Efficient Prompting via Dynamic In-Context Learning","created":"2023-05-18","cited_by_count":18,"area":null},{"id":"2305.13016","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","created":"2023-05-22","cited_by_count":15,"area":null},{"id":"2403.06914","title":"MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning","created":"2024-03-11","cited_by_count":15,"area":null},{"id":"2507.22887","title":"Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning","created":"2025-07-30","cited_by_count":13,"area":null},{"id":"2501.04070","title":"More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives","created":"2025-01-07","cited_by_count":12,"area":null},{"id":"2505.11739","title":"ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training","created":"2025-05-16","cited_by_count":12,"area":null},{"id":"2405.14660","title":"Implicit In-context Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2406.01224","title":"Demonstration Augmentation for Zero-shot In-context Learning","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2410.01288","title":"Mitigating Copy Bias in In-Context Learning through Neuron Pruning","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2305.19402","title":"Contextual Vision Transformers for Robust Representation Learning","created":"2023-05-30","cited_by_count":10,"area":null},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2307.02690","title":"Scaling In-Context Demonstrations with Structured Attention","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2408.13987","title":"Focused Large Language Models are Stable Many-Shot Learners","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2407.00100","title":"Enhancing In-Context Learning via Implicit Demonstration Augmentation","created":"2024-06-27","cited_by_count":6,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2403.17552","title":"Naive Bayes-based Context Extension for Large Language Models","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2406.13185","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2405.16579","title":"Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2506.04650","title":"Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2503.14488","title":"Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2507.16217","title":"Towards Compute-Optimal Many-Shot In-Context Learning","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2401.11323","title":"Identifying and Analyzing Performance-Critical Tokens in Large Language Models","created":"2024-01-20","cited_by_count":2,"area":null},{"id":"2501.15708","title":"StaICC: Standardized Evaluation for Classification Task in In-context Learning","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2505.01110","title":"MateICL: Mitigating Attention Dispersion in Large-Scale In-Context Learning","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2506.00507","title":"Exploring In-context Example Generation for Machine Translation","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2507.08021","title":"Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.19493","title":"What is the Best Sequence Length for BABYLM?","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2402.09954","title":"Crafting a Good Prompt or Providing Exemplary Dialogues? A Study of In-Context Learning for Persona-based Dialogue Generation","created":"2024-02-15","cited_by_count":1,"area":null},{"id":"2404.00570","title":"ParaICL: Towards Parallel In-Context Learning","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2408.03841","title":"MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models","created":"2024-08-07","cited_by_count":1,"area":null},{"id":"2506.23146","title":"Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2307.14856","title":"Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2310.12300","title":"Measuring Pointwise $\\mathcal{V}$-Usable Information In-Context-ly","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2411.19581","title":"In-Context Learning with Noisy Labels","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2507.18340","title":"TDR: Task-Decoupled Retrieval with Fine-Grained LLM Feedback for In-Context Learning","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2604.17512","title":"ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}