{"list":"other","total":61,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"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":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"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":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"2402.04792","title":"Direct Language Model Alignment from Online AI Feedback","created":"2024-02-07","cited_by_count":260},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"1403.5556","title":"Learning to Optimize via Information-Directed Sampling","created":"2014-03-21","cited_by_count":168},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99},{"id":"1910.00762","title":"Accelerating Deep Learning by Focusing on the Biggest Losers","created":"2019-10-02","cited_by_count":94},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80},{"id":"2406.16218","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","created":"2024-06-23","cited_by_count":69},{"id":"2402.08114","title":"Active Preference Learning for Large Language Models","created":"2024-02-12","cited_by_count":58},{"id":"1907.04371","title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","created":"2019-07-09","cited_by_count":51},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47},{"id":"2402.00396","title":"Efficient Exploration for LLMs","created":"2024-02-01","cited_by_count":45},{"id":"2407.00695","title":"Learning Formal Mathematics From Intrinsic Motivation","created":"2024-06-30","cited_by_count":45},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43},{"id":"1604.07101","title":"Double Thompson Sampling for Dueling Bandits","created":"2016-04-25","cited_by_count":42},{"id":"2102.09468","title":"Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization","created":"2021-02-18","cited_by_count":31},{"id":"2303.03376","title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","created":"2023-03-06","cited_by_count":31},{"id":"2409.19605","title":"The Crucial Role of Samplers in Online Direct Preference Optimization","created":"2024-09-29","cited_by_count":27},{"id":"2405.16434","title":"The Importance of Directional Feedback for LLM-based Optimizers","created":"2024-05-26","cited_by_count":26},{"id":"2406.01660","title":"Self-Improving Robust Preference Optimization","created":"2024-06-03","cited_by_count":19},{"id":"2402.12284","title":"Refining Minimax Regret for Unsupervised Environment Design","created":"2024-02-19","cited_by_count":18},{"id":"1910.08475","title":"On Warm-Starting Neural Network Training","created":"2019-10-18","cited_by_count":9},{"id":"1812.00491","title":"Adversarial Domain Randomization","created":"2018-12-03","cited_by_count":5},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2}],"next_cursor":null}