{"total":72,"rows":[{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512,"area":null},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648,"area":null},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345,"area":null},{"id":"2304.11082","title":"Fundamental Limitations of Alignment in Large Language Models","created":"2023-04-19","cited_by_count":155,"area":"alignment"},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149,"area":null},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148,"area":null},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115,"area":null},{"id":"2307.15936","title":"A Theory for Emergence of Complex Skills in Language Models","created":"2023-07-29","cited_by_count":113,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2306.04891","title":"In-Context Learning through the Bayesian Prism","created":"2023-06-08","cited_by_count":83,"area":null},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49,"area":null},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46,"area":"wm"},{"id":"2211.14699","title":"A Theoretical Study of Inductive Biases in Contrastive Learning","created":"2022-11-27","cited_by_count":40,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","cited_by_count":37,"area":null},{"id":"2109.03537","title":"On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets","created":"2021-09-08","cited_by_count":25,"area":null},{"id":"2110.02501","title":"On the Surrogate Gap between Contrastive and Supervised Losses","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"area":null},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2303.01566","title":"On the Provable Advantage of Unsupervised Pretraining","created":"2023-03-02","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2409.19044","title":"On the Inductive Bias of Stacking Towards Improving Reasoning","created":"2024-09-27","cited_by_count":19,"area":"lr"},{"id":"2104.05694","title":"On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies","created":"2021-04-12","cited_by_count":18,"area":null},{"id":"2406.02611","title":"LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","cited_by_count":17,"area":null},{"id":"2309.13692","title":"Regularization and Optimal Multiclass Learning","created":"2023-09-24","cited_by_count":15,"area":null},{"id":"2205.14082","title":"AANG: Automating Auxiliary Learning","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2406.04823","title":"BERTs are Generative In-Context Learners","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2103.10334","title":"Structure Inducing Pre-Training","created":"2021-03-18","cited_by_count":10,"area":null},{"id":"2103.03568","title":"Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis","created":"2021-03-05","cited_by_count":9,"area":null},{"id":"2311.09006","title":"Data Similarity is Not Enough to Explain Language Model Performance","created":"2023-11-15","cited_by_count":9,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2505.13406","title":"AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2109.07458","title":"Comparing Text Representations: A Theory-Driven Approach","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2203.12881","title":"Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2412.05710","title":"PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks","created":"2024-12-07","cited_by_count":5,"area":null},{"id":"2511.03114","title":"An Augmentation Overlap Theory of Contrastive Learning","created":"2025-11-05","cited_by_count":5,"area":null},{"id":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2202.09305","title":"Masked prediction tasks: a parameter identifiability view","created":"2022-02-18","cited_by_count":4,"area":null},{"id":"2210.02881","title":"Antibody Representation Learning for Drug Discovery","created":"2022-10-05","cited_by_count":4,"area":null},{"id":"2312.14285","title":"Probing Biological and Artificial Neural Networks with Task-dependent Neural Manifolds","created":"2023-12-21","cited_by_count":4,"area":null},{"id":"2411.12600","title":"Provable unlearning in topic modeling and downstream tasks","created":"2024-11-19","cited_by_count":4,"area":"safety"},{"id":"2203.03539","title":"Understanding The Robustness of Self-supervised Learning Through Topic Modeling","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2207.06911","title":"Improving self-supervised pretraining models for epileptic seizure detection from EEG data","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2309.02011","title":"Representation Learning Dynamics of Self-Supervised Models","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2212.03760","title":"Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2310.17271","title":"Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2506.01265","title":"Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2208.02252","title":"GROWN+UP: A Graph Representation Of a Webpage Network Utilizing Pre-training","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2402.06884","title":"Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning","created":"2024-02-10","cited_by_count":1,"area":null},{"id":"2501.03166","title":"Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2505.11183","title":"On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2609.01244","title":"Post-Training Science for Supervised Fine-Tuning","created":"2026-09-01","cited_by_count":1,"area":"moe"},{"id":"2109.04400","title":"Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph","created":"2021-09-09","cited_by_count":0,"area":null},{"id":"2401.12295","title":"Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2407.12850","title":"Limits to Predicting Online Speech Using Large Language Models","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2410.00699","title":"Investigating the Impact of Model Complexity in Large Language Models","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2412.20057","title":"\"My life is miserable, have to sign 500 autographs everyday\": Exposing Humblebragging, the Brags in Disguise","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2509.15676","title":"KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2609.38446","title":"What Pretraining and Midtraining Make Learnable from Rewards?","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}