{"list":"other","total":76,"rows":[{"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188},{"id":"1902.00098","title":"The Second Conversational Intelligence Challenge (ConvAI2)","created":"2019-01-31","cited_by_count":179},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135},{"id":"2406.05925","title":"Hello Again! LLM-powered Personalized Agent for Long-term Dialogue","created":"2024-06-09","cited_by_count":123},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122},{"id":"2411.00027","title":"Personalization of Large Language Models: A Survey","created":"2024-10-29","cited_by_count":104},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103},{"id":"2206.03761","title":"A Survey on the Fairness of Recommender Systems","created":"2022-06-08","cited_by_count":102},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98},{"id":"2407.11016","title":"LongLaMP: A Benchmark for Personalized Long-form Text Generation","created":"2024-06-27","cited_by_count":97},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94},{"id":"2311.09180","title":"Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers","created":"2023-11-15","cited_by_count":92},{"id":"2307.16376","title":"When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities","created":"2023-07-31","cited_by_count":90},{"id":"2401.08565","title":"Tuning Language Models by Proxy","created":"2024-01-16","cited_by_count":89},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79},{"id":"2405.00254","title":"RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation","created":"2024-04-30","cited_by_count":74},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64},{"id":"2310.12962","title":"An Emulator for Fine-Tuning Large Language Models using Small Language Models","created":"2023-10-19","cited_by_count":61},{"id":"2309.15028","title":"Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding","created":"2023-09-26","cited_by_count":60},{"id":"2406.02888","title":"HYDRA: Model Factorization Framework for Black-Box LLM Personalization","created":"2024-06-05","cited_by_count":60},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49},{"id":"2308.07968","title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","created":"2023-08-15","cited_by_count":48},{"id":"2407.11484","title":"The Oscars of AI Theater: A Survey on Role-Playing with Language Models","created":"2024-07-16","cited_by_count":48},{"id":"2309.11696","title":"LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination","created":"2023-09-21","cited_by_count":46},{"id":"2403.17141","title":"MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models","created":"2024-03-25","cited_by_count":44},{"id":"2309.03126","title":"Everyone Deserves A Reward: Learning Customized Human Preferences","created":"2023-09-06","cited_by_count":43},{"id":"2310.00152","title":"Learning to Rewrite Prompts for Personalized Text Generation","created":"2023-09-29","cited_by_count":40},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39},{"id":"2409.08069","title":"TravelAgent: An AI Assistant for Personalized Travel Planning","created":"2024-09-12","cited_by_count":39},{"id":"2411.07037","title":"LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios","created":"2024-11-11","cited_by_count":33},{"id":"2406.18678","title":"Few-shot Personalization of LLMs with Mis-aligned Responses","created":"2024-06-26","cited_by_count":32},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29},{"id":"2312.17257","title":"Personalized Large Language Model Assistant with Evolving Conditional Memory","created":"2023-12-22","cited_by_count":25},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25},{"id":"2312.15907","title":"Align on the Fly: Adapting Chatbot Behavior to Established Norms","created":"2023-12-26","cited_by_count":23},{"id":"2409.09510","title":"Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models","created":"2024-09-14","cited_by_count":21},{"id":"2409.17819","title":"Inference-Time Language Model Alignment via Integrated Value Guidance","created":"2024-09-26","cited_by_count":19},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18},{"id":"2406.18187","title":"Selective Prompting Tuning for Personalized Conversations with LLMs","created":"2024-06-26","cited_by_count":16},{"id":"2302.00907","title":"History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System","created":"2023-02-02","cited_by_count":15},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15},{"id":"2209.12613","title":"Factual and Informative Review Generation for Explainable Recommendation","created":"2022-09-12","cited_by_count":14},{"id":"2306.12680","title":"Recent Developments in Recommender Systems: A Survey","created":"2023-06-22","cited_by_count":14},{"id":"2411.19128","title":"Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures","created":"2024-11-28","cited_by_count":12},{"id":"2404.13238","title":"Personalized Wireless Federated Learning for Large Language Models","created":"2024-04-20","cited_by_count":11},{"id":"2406.15352","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","created":"2024-06-21","cited_by_count":10},{"id":"2406.17588","title":"LongIns: A Challenging Long-context Instruction-based Exam for LLMs","created":"2024-06-25","cited_by_count":6},{"id":"2407.00693","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","created":"2024-06-30","cited_by_count":6},{"id":"2404.16115","title":"Online Personalizing White-box LLMs Generation with Neural Bandits","created":"2024-04-24","cited_by_count":5},{"id":"2410.13785","title":"PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment","created":"2024-10-17","cited_by_count":2}],"next_cursor":null}