{"list":"other","total":52,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"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":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"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":"2308.08998","title":"Reinforced Self-Training (ReST) for Language Modeling","created":"2023-08-17","cited_by_count":500},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","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":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2306.17492","title":"Preference Ranking Optimization for Human Alignment","created":"2023-06-30","cited_by_count":285},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2211.15006","title":"Fine-tuning language models to find agreement among humans with diverse preferences","created":"2022-11-28","cited_by_count":189},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123},{"id":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78},{"id":"2312.02439","title":"Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation","created":"2023-12-05","cited_by_count":56},{"id":"2307.12950","title":"RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment","created":"2023-07-24","cited_by_count":43},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36},{"id":"2402.12366","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","created":"2024-02-19","cited_by_count":36},{"id":"2205.01497","title":"Semantic Diversity in Dialogue with Natural Language Inference","created":"2022-05-03","cited_by_count":29},{"id":"2306.04563","title":"ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models","created":"2023-06-07","cited_by_count":24},{"id":"2106.03300","title":"Sum of Ranked Range Loss for Supervised Learning","created":"2021-06-07","cited_by_count":23},{"id":"2311.14115","title":"A density estimation perspective on learning from pairwise human preferences","created":"2023-11-23","cited_by_count":23},{"id":"2404.13599","title":"\"A good pun is its own reword\": Can Large Language Models Understand Puns?","created":"2024-04-21","cited_by_count":21},{"id":"1706.05378","title":"A framework for Multi-A(rmed)/B(andit) testing with online FDR control","created":"2017-06-16","cited_by_count":17},{"id":"1506.08126","title":"Humor in Collective Discourse: Unsupervised Funniness Detection in the New Yorker Cartoon Caption Contest","created":"2015-06-26","cited_by_count":16},{"id":"2310.16763","title":"SuperHF: Supervised Iterative Learning from Human Feedback","created":"2023-10-25","cited_by_count":10}],"next_cursor":null}