{"list":"other","total":54,"rows":[{"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":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2309.03409","title":"Large Language Models as Optimizers","created":"2023-09-07","cited_by_count":864},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"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":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331},{"id":"2404.02060","title":"Long-context LLMs Struggle with Long In-context Learning","created":"2024-04-02","cited_by_count":286},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155},{"id":"2402.05133","title":"Personalized Language Modeling from Personalized Human Feedback","created":"2024-02-06","cited_by_count":132},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84},{"id":"2404.04326","title":"Hypothesis Generation with Large Language Models","created":"2024-04-05","cited_by_count":71},{"id":"2310.11523","title":"Group Preference Optimization: Few-Shot Alignment of Large Language Models","created":"2023-10-17","cited_by_count":63},{"id":"2502.16923","title":"A Systematic Survey of Automatic Prompt Optimization Techniques","created":"2025-02-24","cited_by_count":63},{"id":"2304.00008","title":"On the Creativity of Large Language Models","created":"2023-03-27","cited_by_count":57},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54},{"id":"2310.20081","title":"Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models","created":"2023-10-30","cited_by_count":45},{"id":"2503.02450","title":"Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization","created":"2025-03-04","cited_by_count":45},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42},{"id":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38},{"id":"2405.17346","title":"Prompt Optimization with Human Feedback","created":"2024-05-27","cited_by_count":35},{"id":"2505.22257","title":"Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training","created":"2025-05-28","cited_by_count":34},{"id":"2409.11901","title":"LLMs + Persona-Plug = Personalized LLMs","created":"2024-09-18","cited_by_count":32},{"id":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30},{"id":"2506.02368","title":"NextQuill: Causal Preference Modeling for Enhancing LLM Personalization","created":"2025-06-03","cited_by_count":30},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27},{"id":"2402.05810","title":"Transparent and Scrutable Recommendations Using Natural Language User Profiles","created":"2024-02-08","cited_by_count":24},{"id":"2205.09403","title":"On Natural Language User Profiles for Transparent and Scrutable Recommendation","created":"2022-05-19","cited_by_count":23},{"id":"2402.15623","title":"Language-Based User Profiles for Recommendation","created":"2024-02-23","cited_by_count":18},{"id":"2502.12633","title":"One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction","created":"2025-02-18","cited_by_count":17},{"id":"2409.04421","title":"RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs","created":"2024-09-06","cited_by_count":13},{"id":"2404.06762","title":"Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems","created":"2024-04-10","cited_by_count":12},{"id":"2412.08812","title":"Test-Time Alignment via Hypothesis Reweighting","created":"2024-12-11","cited_by_count":11},{"id":"2410.18870","title":"End-to-end Training for Recommendation with Language-based User Profiles","created":"2024-10-24","cited_by_count":10},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10},{"id":"2505.00038","title":"HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation","created":"2025-04-29","cited_by_count":7},{"id":"2410.03905","title":"PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models","created":"2024-10-04","cited_by_count":5},{"id":"2408.07294","title":"SumRecom: A Personalized Summarization Approach by Learning from Users' Feedback","created":"2024-08-02","cited_by_count":4},{"id":"2412.07998","title":"RALI@TREC iKAT 2024: Achieving Personalization via Retrieval Fusion in Conversational Search","created":"2024-12-11","cited_by_count":3},{"id":"2504.03965","title":"Automating Personalization: Prompt Optimization for Recommendation Reranking","created":"2025-04-04","cited_by_count":2},{"id":"2505.17156","title":"PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG","created":"2025-05-22","cited_by_count":2},{"id":"2506.18269","title":"Co-persona: Leveraging LLMs and Expert Collaboration to Understand User Personas through Social Media Data Analysis","created":"2025-06-23","cited_by_count":2}],"next_cursor":null}