{"list":"other","total":52,"rows":[{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"2306.15895","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","created":"2023-06-28","cited_by_count":232},{"id":"2309.05196","title":"Does Writing with Language Models Reduce Content Diversity?","created":"2023-09-11","cited_by_count":192},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174},{"id":"2407.01082","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","created":"2024-07-01","cited_by_count":150},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130},{"id":"2004.02990","title":"Evaluating the Evaluation of Diversity in Natural Language Generation","created":"2020-04-06","cited_by_count":129},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125},{"id":"2312.16682","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","created":"2023-12-27","cited_by_count":108},{"id":"2004.10450","title":"Trading Off Diversity and Quality in Natural Language Generation","created":"2020-04-22","cited_by_count":96},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58},{"id":"2403.00553","title":"Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores","created":"2024-03-01","cited_by_count":50},{"id":"2404.10859","title":"Forcing Diffuse Distributions out of Language Models","created":"2024-04-16","cited_by_count":48},{"id":"2310.13032","title":"Quality-Diversity through AI Feedback","created":"2023-10-19","cited_by_count":40},{"id":"2412.10271","title":"Benchmarking Linguistic Diversity of Large Language Models","created":"2024-12-13","cited_by_count":38},{"id":"2402.10693","title":"Exploring Precision and Recall to assess the quality and diversity of LLMs","created":"2024-02-16","cited_by_count":29},{"id":"2409.11547","title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","created":"2024-09-17","cited_by_count":17},{"id":"2410.12138","title":"Preference Optimization with Multi-Sample Comparisons","created":"2024-10-16","cited_by_count":16},{"id":"2409.11378","title":"Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement","created":"2024-09-17","cited_by_count":13},{"id":"2412.03822","title":"Beyond the Binary: Capturing Diverse Preferences With Reward Regularization","created":"2024-12-05","cited_by_count":11},{"id":"2411.09661","title":"Adaptive Decoding via Latent Preference Optimization","created":"2024-11-14","cited_by_count":10},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9},{"id":"2410.19471","title":"Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization","created":"2024-10-25","cited_by_count":5},{"id":"2501.00747","title":"DIVE: Diversified Iterative Self-Improvement","created":"2025-01-01","cited_by_count":3}],"next_cursor":null}