{"list":"other","total":49,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"2107.12028","title":"Parametric Contrastive Learning","created":"2021-07-26","cited_by_count":217},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"2401.10529","title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","created":"2024-01-19","cited_by_count":94},{"id":"2310.19596","title":"LLMaAA: Making Large Language Models as Active Annotators","created":"2023-10-30","cited_by_count":79},{"id":"2405.15973","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","created":"2024-05-24","cited_by_count":74},{"id":"2103.15042","title":"Distilling Virtual Examples for Long-tailed Recognition","created":"2021-03-28","cited_by_count":72},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48},{"id":"1909.09389","title":"Sampling Bias in Deep Active Classification: An Empirical Study","created":"2019-09-20","cited_by_count":36},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35},{"id":"2109.04712","title":"Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution","created":"2021-09-10","cited_by_count":35},{"id":"2402.11161","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","created":"2024-02-17","cited_by_count":31},{"id":"2003.13960","title":"Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model","created":"2020-03-31","cited_by_count":28},{"id":"2403.09606","title":"Large Language Models and Causal Inference in Collaboration: A Survey","created":"2024-03-14","cited_by_count":26},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22},{"id":"2406.12114","title":"Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation","created":"2024-06-17","cited_by_count":20},{"id":"2004.08046","title":"Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space","created":"2020-04-17","cited_by_count":17},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17},{"id":"2310.19019","title":"TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise","created":"2023-10-29","cited_by_count":15},{"id":"2306.00899","title":"Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices","created":"2023-06-01","cited_by_count":13},{"id":"2302.09236","title":"Scalable Prompt Generation for Semi-supervised Learning with Language Models","created":"2023-02-18","cited_by_count":11},{"id":"2303.07626","title":"CAT: Causal Audio Transformer for Audio Classification","created":"2023-03-14","cited_by_count":10},{"id":"2401.16348","title":"Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis","created":"2024-01-29","cited_by_count":10},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9},{"id":"2404.02444","title":"The Promises and Pitfalls of Using Language Models to Measure Instruction Quality in Education","created":"2024-04-03","cited_by_count":9},{"id":"2205.05461","title":"Making Pretrained Language Models Good Long-tailed Learners","created":"2022-05-11","cited_by_count":8},{"id":"2205.09460","title":"Why only Micro-F1? Class Weighting of Measures for Relation Classification","created":"2022-05-19","cited_by_count":8},{"id":"2305.06557","title":"Long-Tailed Question Answering in an Open World","created":"2023-05-11","cited_by_count":7},{"id":"2310.17325","title":"C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder","created":"2023-10-26","cited_by_count":7}],"next_cursor":null}