{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"1909.09369","title":"FACE: Feasible and Actionable Counterfactual Explanations","created":"2019-09-20","cited_by_count":233},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176},{"id":"2010.10596","title":"Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review","created":"2020-10-20","cited_by_count":174},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143},{"id":"1811.03402","title":"A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective","created":"2018-11-08","cited_by_count":112},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93},{"id":"2402.09668","title":"How to Train Data-Efficient LLMs","created":"2024-02-15","cited_by_count":93},{"id":"2006.13132","title":"On Counterfactual Explanations under Predictive Multiplicity","created":"2020-06-23","cited_by_count":74},{"id":"2010.02114","title":"Explaining The Efficacy of Counterfactually Augmented Data","created":"2020-10-05","cited_by_count":65},{"id":"1908.01851","title":"Self-Knowledge Distillation in Natural Language Processing","created":"2019-08-02","cited_by_count":60},{"id":"2305.11997","title":"Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees","created":"2023-05-19","cited_by_count":45},{"id":"2111.00358","title":"A Survey on the Robustness of Feature Importance and Counterfactual Explanations","created":"2021-10-30","cited_by_count":39},{"id":"2405.00722","title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","created":"2024-04-26","cited_by_count":31},{"id":"2212.10534","title":"DISCO: Distilling Counterfactuals with Large Language Models","created":"2022-12-20","cited_by_count":30},{"id":"2407.16154","title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","created":"2024-07-23","cited_by_count":26},{"id":"2504.14772","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","created":"2025-04-20","cited_by_count":26},{"id":"2008.12094","title":"MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation","created":"2020-08-27","cited_by_count":18},{"id":"2405.04793","title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","created":"2024-05-08","cited_by_count":18},{"id":"1503.05296","title":"Efficient Machine Learning for Big Data: A Review","created":"2015-03-18","cited_by_count":17},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17},{"id":"2405.05369","title":"Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory","created":"2024-05-08","cited_by_count":14},{"id":"2402.03099","title":"Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases","created":"2024-02-05","cited_by_count":13},{"id":"2405.13448","title":"Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning","created":"2024-05-22","cited_by_count":13},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9},{"id":"2310.06557","title":"Data efficient deep learning for medical image analysis: A survey","created":"2023-10-10","cited_by_count":6},{"id":"2407.04173","title":"Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs","created":"2024-07-04","cited_by_count":6},{"id":"2408.09722","title":"Towards Few-Shot Learning in the Open World: A Review and Beyond","created":"2024-08-19","cited_by_count":5},{"id":"2411.02643","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","created":"2024-11-04","cited_by_count":5},{"id":"2508.18933","title":"VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation","created":"2025-08-26","cited_by_count":3},{"id":"2211.00369","title":"A General Search-based Framework for Generating Textual Counterfactual Explanations","created":"2022-11-01","cited_by_count":2},{"id":"2502.17613","title":"Flexible Counterfactual Explanations with Generative Models","created":"2025-02-24","cited_by_count":2}],"next_cursor":null}