{"list":"other","total":104,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"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":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515},{"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":"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":"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":"2402.01622","title":"TravelPlanner: A Benchmark for Real-World Planning with Language Agents","created":"2024-02-02","cited_by_count":392},{"id":"2305.00447","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","created":"2023-04-30","cited_by_count":337},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267},{"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":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201},{"id":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200},{"id":"2304.10149","title":"Is ChatGPT a Good Recommender? A Preliminary Study","created":"2023-04-20","cited_by_count":193},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175},{"id":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155},{"id":"2305.13731","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","created":"2023-05-23","cited_by_count":149},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148},{"id":"2311.09528","title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","created":"2023-11-16","cited_by_count":142},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133},{"id":"2406.05925","title":"Hello Again! LLM-powered Personalized Agent for Long-term Dialogue","created":"2024-06-09","cited_by_count":123},{"id":"2305.06474","title":"Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction","created":"2023-05-10","cited_by_count":116},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111},{"id":"2203.05797","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","created":"2022-03-11","cited_by_count":108},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99},{"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":"2310.02374","title":"Conversational Health Agents: A Personalized LLM-Powered Agent Framework","created":"2023-10-03","cited_by_count":92},{"id":"2403.19318","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","created":"2024-03-28","cited_by_count":77},{"id":"2402.13598","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","created":"2024-02-21","cited_by_count":76},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75},{"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":"2407.19056","title":"OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation","created":"2024-07-26","cited_by_count":70},{"id":"2009.07602","title":"UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation","created":"2020-09-16","cited_by_count":60},{"id":"2406.07925","title":"FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning","created":"2024-06-12","cited_by_count":59},{"id":"2402.15235","title":"MACRec: a Multi-Agent Collaboration Framework for Recommendation","created":"2024-02-23","cited_by_count":58},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57},{"id":"2308.07968","title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","created":"2023-08-15","cited_by_count":48},{"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":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43},{"id":"2405.14231","title":"From Role-Play to Drama-Interaction: An LLM Solution","created":"2024-05-23","cited_by_count":42},{"id":"2310.00152","title":"Learning to Rewrite Prompts for Personalized Text Generation","created":"2023-09-29","cited_by_count":40},{"id":"2409.08069","title":"TravelAgent: An AI Assistant for Personalized Travel Planning","created":"2024-09-12","cited_by_count":39},{"id":"2401.13256","title":"UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems","created":"2024-01-24","cited_by_count":38},{"id":"2402.07204","title":"ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning","created":"2024-02-11","cited_by_count":33},{"id":"2308.09904","title":"RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents","created":"2023-08-19","cited_by_count":30},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29},{"id":"2402.01469","title":"AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback","created":"2024-02-02","cited_by_count":25},{"id":"2310.18816","title":"Adaptive Test-Time Personalization for Federated Learning","created":"2023-10-28","cited_by_count":23},{"id":"2306.10702","title":"A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News","created":"2023-06-19","cited_by_count":19},{"id":"2402.18240","title":"Prospect Personalized Recommendation on Large Language Model-based Agent Platform","created":"2024-02-28","cited_by_count":19},{"id":"2502.07663","title":"Human Decision-making is Susceptible to AI-driven Manipulation","created":"2025-02-11","cited_by_count":19},{"id":"2406.18187","title":"Selective Prompting Tuning for Personalized Conversations with LLMs","created":"2024-06-26","cited_by_count":16},{"id":"2408.00960","title":"PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting","created":"2024-08-02","cited_by_count":14},{"id":"2306.01815","title":"Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scale","created":"2023-06-02","cited_by_count":12},{"id":"2406.17255","title":"MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning","created":"2024-06-25","cited_by_count":12},{"id":"2402.13399","title":"Learning and Sustaining Shared Normative Systems via Bayesian Rule Induction in Markov Games","created":"2024-02-20","cited_by_count":11},{"id":"2404.06364","title":"SurveyAgent: A Conversational System for Personalized and Efficient Research Survey","created":"2024-04-09","cited_by_count":11},{"id":"2409.04593","title":"Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance","created":"2024-09-06","cited_by_count":8},{"id":"2410.16780","title":"Beyond Retrieval: Generating Narratives in Conversational Recommender Systems","created":"2024-10-22","cited_by_count":8},{"id":"2205.04279","title":"Aligned with Whom? Direct and social goals for AI systems","created":"2022-05-09","cited_by_count":7},{"id":"2501.09099","title":"Drama Llama: An LLM-Powered Storylets Framework for Authorable Responsiveness in Interactive Narrative","created":"2025-01-15","cited_by_count":7},{"id":"2412.08969","title":"Deep Learning Model Security: Threats and Defenses","created":"2024-12-12","cited_by_count":4},{"id":"2407.21593","title":"LLM-for-X: Application-agnostic Integration of Large Language Models to Support Personal Writing Workflows","created":"2024-07-31","cited_by_count":3},{"id":"2501.11002","title":"pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup","created":"2025-01-19","cited_by_count":3}],"next_cursor":"100"}