{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"1605.07723","title":"Data Programming: Creating Large Training Sets, Quickly","created":"2016-05-25","cited_by_count":246},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123},{"id":"1512.02433","title":"Minimum Risk Training for Neural Machine Translation","created":"2015-12-08","cited_by_count":115},{"id":"2310.00429","title":"On the Stability of Iterative Retraining of Generative Models on their own Data","created":"2023-09-30","cited_by_count":100},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82},{"id":"2001.08837","title":"Graph Constrained Reinforcement Learning for Natural Language Action Spaces","created":"2020-01-23","cited_by_count":80},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72},{"id":"2307.03025","title":"Style Over Substance: Evaluation Biases for Large Language Models","created":"2023-07-06","cited_by_count":70},{"id":"1902.09145","title":"DDFlow: Learning Optical Flow with Unlabeled Data Distillation","created":"2019-02-25","cited_by_count":63},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44},{"id":"2106.01023","title":"One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers","created":"2021-06-02","cited_by_count":40},{"id":"2311.00913","title":"Self-Influence Guided Data Reweighting for Language Model Pre-training","created":"2023-11-02","cited_by_count":37},{"id":"2401.04578","title":"Effective pruning of web-scale datasets based on complexity of concept clusters","created":"2024-01-09","cited_by_count":34},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32},{"id":"1704.06497","title":"Bandit Structured Prediction for Neural Sequence-to-Sequence Learning","created":"2017-04-21","cited_by_count":31},{"id":"2004.03672","title":"Dynamic Data Selection and Weighting for Iterative Back-Translation","created":"2020-04-07","cited_by_count":25},{"id":"2306.03208","title":"NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks","created":"2023-06-05","cited_by_count":20},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18},{"id":"1709.09346","title":"Cold-Start Reinforcement Learning with Softmax Policy Gradient","created":"2017-09-27","cited_by_count":15},{"id":"2301.02057","title":"TextDescriptives: A Python package for calculating a large variety of metrics from text","created":"2023-01-05","cited_by_count":13},{"id":"2104.07541","title":"Reward Optimization for Neural Machine Translation with Learned Metrics","created":"2021-04-15","cited_by_count":12},{"id":"2206.11526","title":"A Survey on Learnable Evolutionary Algorithms for Scalable Multiobjective Optimization","created":"2022-06-23","cited_by_count":7},{"id":"2302.07215","title":"Multi-teacher knowledge distillation as an effective method for compressing ensembles of neural networks","created":"2023-02-14","cited_by_count":6},{"id":"2204.00548","title":"Unified and Effective Ensemble Knowledge Distillation","created":"2022-04-01","cited_by_count":5}],"next_cursor":null}