{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"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":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149},{"id":"2309.10105","title":"Understanding Catastrophic Forgetting in Language Models via Implicit Inference","created":"2023-09-18","cited_by_count":144},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94},{"id":"2309.16349","title":"Human Feedback is not Gold Standard","created":"2023-09-28","cited_by_count":83},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75},{"id":"2301.01967","title":"A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies","created":"2023-01-05","cited_by_count":59},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56},{"id":"2405.05417","title":"Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models","created":"2024-05-08","cited_by_count":46},{"id":"2405.20850","title":"Improving Reward Models with Synthetic Critiques","created":"2024-05-31","cited_by_count":44},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35},{"id":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","cited_by_count":35},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25},{"id":"2305.01711","title":"Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner","created":"2023-05-02","cited_by_count":23},{"id":"2405.13907","title":"Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries","created":"2024-05-22","cited_by_count":15},{"id":"2406.17803","title":"Understanding the Role of User Profile in the Personalization of Large Language Models","created":"2024-06-22","cited_by_count":11}],"next_cursor":null}