{"list":"other","total":68,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"1901.08149","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","created":"2019-01-23","cited_by_count":188},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148},{"id":"1910.07931","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","created":"2019-10-17","cited_by_count":145},{"id":"2210.02627","title":"Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering","created":"2022-10-06","cited_by_count":127},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90},{"id":"1905.10033","title":"Personalizing Dialogue Agents via Meta-Learning","created":"2019-05-24","cited_by_count":83},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78},{"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":"2203.15144","title":"Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support","created":"2022-03-28","cited_by_count":68},{"id":"2405.19332","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","created":"2024-05-29","cited_by_count":63},{"id":"2104.13030","title":"A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation","created":"2021-04-27","cited_by_count":59},{"id":"2402.08114","title":"Active Preference Learning for Large Language Models","created":"2024-02-12","cited_by_count":58},{"id":"2004.12316","title":"Towards Persona-Based Empathetic Conversational Models","created":"2020-04-26","cited_by_count":53},{"id":"2402.10038","title":"RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models","created":"2024-02-15","cited_by_count":48},{"id":"2403.09738","title":"Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation","created":"2024-03-13","cited_by_count":48},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44},{"id":"2105.03354","title":"The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems","created":"2021-05-07","cited_by_count":39},{"id":"2403.05534","title":"Bayesian Preference Elicitation with Language Models","created":"2024-03-08","cited_by_count":34},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33},{"id":"2312.12009","title":"Active Preference Inference using Language Models and Probabilistic Reasoning","created":"2023-12-19","cited_by_count":29},{"id":"2402.09660","title":"User Modeling and User Profiling: A Comprehensive Survey","created":"2024-02-15","cited_by_count":29},{"id":"2201.06657","title":"A Literature Survey of Recent Advances in Chatbots","created":"2022-01-17","cited_by_count":26},{"id":"2204.09867","title":"A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation","created":"2022-04-21","cited_by_count":25},{"id":"2306.04930","title":"When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming","created":"2023-06-08","cited_by_count":25},{"id":"2210.15088","title":"Personalized Dialogue Generation with Persona-Adaptive Attention","created":"2022-10-27","cited_by_count":24},{"id":"2405.18027","title":"TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models","created":"2024-05-28","cited_by_count":22},{"id":"2405.17974","title":"Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations","created":"2024-05-28","cited_by_count":20},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20},{"id":"2204.07372","title":"A Personalized Dialogue Generator with Implicit User Persona Detection","created":"2022-04-15","cited_by_count":19},{"id":"2409.13093","title":"Guided Profile Generation Improves Personalization with LLMs","created":"2024-09-19","cited_by_count":19},{"id":"2406.18847","title":"Learning Retrieval Augmentation for Personalized Dialogue Generation","created":"2024-06-27","cited_by_count":18},{"id":"2405.00981","title":"Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation","created":"2024-05-02","cited_by_count":17},{"id":"2406.18187","title":"Selective Prompting Tuning for Personalized Conversations with LLMs","created":"2024-06-26","cited_by_count":16},{"id":"2411.00418","title":"Self-Evolved Reward Learning for LLMs","created":"2024-11-01","cited_by_count":16},{"id":"2311.14713","title":"The Rise of the AI Co-Pilot: Lessons for Design from Aviation and Beyond","created":"2023-11-16","cited_by_count":15},{"id":"2403.19279","title":"Fine-Tuning Language Models with Reward Learning on Policy","created":"2024-03-28","cited_by_count":15},{"id":"2202.05971","title":"Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents","created":"2022-02-12","cited_by_count":14},{"id":"2410.03198","title":"PersoBench: Benchmarking Personalized Response Generation in Large Language Models","created":"2024-10-04","cited_by_count":13},{"id":"2403.03102","title":"\"In Dialogues We Learn\": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning","created":"2024-03-05","cited_by_count":10},{"id":"2306.08126","title":"PersonaPKT: Building Personalized Dialogue Agents via Parameter-efficient Knowledge Transfer","created":"2023-06-13","cited_by_count":9},{"id":"2410.23569","title":"RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning","created":"2024-10-31","cited_by_count":9},{"id":"2302.06674","title":"PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue","created":"2023-02-13","cited_by_count":6},{"id":"2407.09512","title":"Design and evaluation of AI copilots -- case studies of retail copilot templates","created":"2024-06-17","cited_by_count":3},{"id":"2308.02542","title":"Collaborative filtering to capture AI user's preferences as norms","created":"2023-08-01","cited_by_count":2},{"id":"2311.10773","title":"User Persona Identification and New Service Adaptation Recommendation","created":"2023-11-15","cited_by_count":2},{"id":"1709.04574","title":"Towards personalized human AI interaction - adapting the behavior of AI agents using neural signatures of subjective interest","created":"2017-09-14","cited_by_count":1}],"next_cursor":null}