{"list":"other","total":126,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267},{"id":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2305.02547","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","created":"2023-05-04","cited_by_count":234},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"1603.06155","title":"A Persona-Based Neural Conversation Model","created":"2016-03-19","cited_by_count":223},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208},{"id":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"1506.05869","title":"A Neural Conversational Model","created":"2015-06-19","cited_by_count":196},{"id":"1902.10909","title":"BERT for Joint Intent Classification and Slot Filling","created":"2019-02-28","cited_by_count":196},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188},{"id":"2502.08691","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","created":"2025-02-12","cited_by_count":186},{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169},{"id":"1808.09637","title":"Decoupling Strategy and Generation in Negotiation Dialogues","created":"2018-08-29","cited_by_count":162},{"id":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"id":"1608.04468","title":"Unbiased Learning-to-Rank with Biased Feedback","created":"2016-08-16","cited_by_count":157},{"id":"2401.01275","title":"CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation","created":"2024-01-02","cited_by_count":143},{"id":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140},{"id":"2406.19226","title":"Simulating Classroom Education with LLM-Empowered Agents","created":"2024-06-27","cited_by_count":127},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118},{"id":"2311.00273","title":"SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations","created":"2023-11-01","cited_by_count":110},{"id":"2502.01600","title":"Reinforcement Learning for Long-Horizon Interactive LLM Agents","created":"2025-02-03","cited_by_count":108},{"id":"2504.08942","title":"AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories","created":"2025-04-11","cited_by_count":108},{"id":"2401.12474","title":"Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment","created":"2024-01-23","cited_by_count":104},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99},{"id":"1909.04847","title":"RecSim: A Configurable Simulation Platform for Recommender Systems","created":"2019-09-11","cited_by_count":94},{"id":"2104.00773","title":"MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation","created":"2021-04-01","cited_by_count":88},{"id":"2503.16527","title":"LLM Generated Persona is a Promise with a Catch","created":"2025-03-18","cited_by_count":81},{"id":"1502.02763","title":"Cascading Bandits: Learning to Rank in the Cascade Model","created":"2015-02-10","cited_by_count":77},{"id":"2404.15993","title":"Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach","created":"2024-04-24","cited_by_count":76},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75},{"id":"1901.09672","title":"Personalized Dialogue Generation with Diversified Traits","created":"2019-01-28","cited_by_count":74},{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71},{"id":"1804.08217","title":"Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems","created":"2018-04-23","cited_by_count":70},{"id":"2312.02913","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","created":"2023-12-05","cited_by_count":70},{"id":"2002.11893","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","created":"2020-02-27","cited_by_count":66},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66},{"id":"1808.00720","title":"RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising","created":"2018-08-02","cited_by_count":65},{"id":"2406.14868","title":"Direct Multi-Turn Preference Optimization for Language Agents","created":"2024-06-21","cited_by_count":64},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56},{"id":"2403.09738","title":"Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation","created":"2024-03-13","cited_by_count":48},{"id":"2006.08732","title":"Evaluating Conversational Recommender Systems via User Simulation","created":"2020-06-15","cited_by_count":47},{"id":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43},{"id":"2408.15787","title":"Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions","created":"2024-08-28","cited_by_count":43},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42},{"id":"2405.14231","title":"From Role-Play to Drama-Interaction: An LLM Solution","created":"2024-05-23","cited_by_count":42},{"id":"2403.08251","title":"Emergence of Social Norms in Generative Agent Societies: Principles and Architecture","created":"2024-03-13","cited_by_count":41},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39},{"id":"2412.16984","title":"LLM-Powered User Simulator for Recommender System","created":"2024-12-22","cited_by_count":39},{"id":"2404.12726","title":"Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works","created":"2024-04-19","cited_by_count":38},{"id":"2404.06711","title":"MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education","created":"2024-04-10","cited_by_count":37},{"id":"2405.13001","title":"Large Language Models for Education: A Survey","created":"2024-05-12","cited_by_count":34},{"id":"1804.10488","title":"Offline Evaluation of Ranking Policies with Click Models","created":"2018-04-27","cited_by_count":32},{"id":"2306.09821","title":"Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System","created":"2023-06-16","cited_by_count":32},{"id":"2403.09142","title":"USimAgent: Large Language Models for Simulating Search Users","created":"2024-03-14","cited_by_count":32},{"id":"2407.12874","title":"SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning","created":"2024-07-16","cited_by_count":32},{"id":"2306.08550","title":"User Simulation for Evaluating Information Access Systems","created":"2023-06-14","cited_by_count":31},{"id":"2112.08619","title":"Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge","created":"2021-12-16","cited_by_count":30},{"id":"2501.01821","title":"SDPO: Segment-Level Direct Preference Optimization for Social Agents","created":"2025-01-03","cited_by_count":30},{"id":"2308.11534","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","created":"2023-08-21","cited_by_count":29},{"id":"1606.02448","title":"Multiple-Play Bandits in the Position-Based Model","created":"2016-06-08","cited_by_count":28},{"id":"2501.04167","title":"Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation","created":"2025-01-07","cited_by_count":27},{"id":"2503.17662","title":"Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning","created":"2025-03-22","cited_by_count":27},{"id":"2504.03206","title":"Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward","created":"2025-04-04","cited_by_count":27},{"id":"2402.17505","title":"BASES: Large-scale Web Search User Simulation with Large Language Model based Agents","created":"2024-02-27","cited_by_count":25},{"id":"2410.04078","title":"TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students","created":"2024-10-05","cited_by_count":25},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24},{"id":"2405.13028","title":"DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues","created":"2024-05-16","cited_by_count":24},{"id":"1805.04803","title":"Zero-Shot Dialog Generation with Cross-Domain Latent Actions","created":"2018-05-13","cited_by_count":23},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22},{"id":"2407.21712","title":"Adaptive Retrieval-Augmented Generation for Conversational Systems","created":"2024-07-31","cited_by_count":22},{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22},{"id":"2407.07053","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","created":"2024-07-09","cited_by_count":21},{"id":"2409.16727","title":"RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems","created":"2024-09-25","cited_by_count":21},{"id":"2507.20152","title":"Goal Alignment in LLM-Based User Simulators for Conversational AI","created":"2025-07-27","cited_by_count":21},{"id":"2306.00774","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","created":"2023-06-01","cited_by_count":19},{"id":"2406.17260","title":"Mitigating Hallucination in Fictional Character Role-Play","created":"2024-06-25","cited_by_count":18},{"id":"2411.13281","title":"VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation","created":"2024-11-20","cited_by_count":18}],"next_cursor":"100"}