{"total":288,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"area":null},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121,"area":null},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2307.15190","title":"f-Divergence Minimization for Sequence-Level Knowledge Distillation","created":"2023-07-27","cited_by_count":114,"area":"distill"},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2203.05797","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","created":"2022-03-11","cited_by_count":108,"area":null},{"id":"2311.13443","title":"Guided Flows for Generative Modeling and Decision Making","created":"2023-11-22","cited_by_count":101,"area":"diffusion"},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"id":"2101.07714","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","created":"2021-01-19","cited_by_count":75,"area":null},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72,"area":"alignment"},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2306.02531","title":"PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model","created":"2023-06-05","cited_by_count":58,"area":"diffusion"},{"id":"2212.09739","title":"LENS: A Learnable Evaluation Metric for Text Simplification","created":"2022-12-19","cited_by_count":54,"area":null},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2303.06433","title":"Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation","created":"2023-03-11","cited_by_count":39,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2109.09519","title":"PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation","created":"2021-09-20","cited_by_count":37,"area":null},{"id":"2310.05280","title":"Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems","created":"2023-10-08","cited_by_count":37,"area":null},{"id":"2210.07109","title":"Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2204.08426","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","created":"2022-04-18","cited_by_count":34,"area":"offlinerl"},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2109.06415","title":"Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction","created":"2021-09-14","cited_by_count":33,"area":null},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","cited_by_count":33,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31,"area":null},{"id":"2111.13359","title":"Neural Collaborative Graph Machines for Table Structure Recognition","created":"2021-11-26","cited_by_count":30,"area":null},{"id":"2204.01440","title":"Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2305.02468","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","created":"2023-05-04","cited_by_count":30,"area":null},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"area":"alignment"},{"id":"2106.06719","title":"Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring","created":"2021-06-12","cited_by_count":29,"area":null},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2203.15108","title":"A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation","created":"2022-03-28","cited_by_count":28,"area":null},{"id":"2410.03777","title":"Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling","created":"2024-10-03","cited_by_count":28,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2201.06657","title":"A Literature Survey of Recent Advances in Chatbots","created":"2022-01-17","cited_by_count":26,"area":null},{"id":"2306.08891","title":"Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation","created":"2023-06-15","cited_by_count":24,"area":null},{"id":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"area":null},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23,"area":null},{"id":"2204.02246","title":"Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization","created":"2022-04-04","cited_by_count":23,"area":null},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"id":"2401.07382","title":"Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation","created":"2024-01-14","cited_by_count":22,"area":"alignment"},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"1812.03509","title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","created":"2018-12-09","cited_by_count":21,"area":"offlinerl"},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2103.13552","title":"Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents","created":"2021-03-25","cited_by_count":20,"area":null},{"id":"2302.01328","title":"IC3: Image Captioning by Committee Consensus","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2402.16041","title":"Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy","created":"2024-02-25","cited_by_count":20,"area":null},{"id":"2206.05395","title":"Why is constrained neural language generation particularly challenging?","created":"2022-06-11","cited_by_count":19,"area":null},{"id":"2210.15777","title":"Reinforced Question Rewriting for Conversational Question Answering","created":"2022-10-27","cited_by_count":19,"area":null},{"id":"2402.10893","title":"RLVF: Learning from Verbal Feedback without Overgeneralization","created":"2024-02-16","cited_by_count":19,"area":"alignment"},{"id":"2406.10278","title":"Prompt-Based Length Controlled Generation with Multiple Control Types","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2106.03410","title":"Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders","created":"2021-06-07","cited_by_count":18,"area":null},{"id":"2108.00308","title":"Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers","created":"2021-07-31","cited_by_count":18,"area":null},{"id":"2109.05140","title":"Refocusing on Relevance: Personalization in NLG","created":"2021-09-10","cited_by_count":18,"area":null},{"id":"2109.15144","title":"A Review of Text Style Transfer using Deep Learning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18,"area":"alignment"},{"id":"2202.10678","title":"Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning","created":"2022-02-22","cited_by_count":18,"area":null},{"id":"2308.07336","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","created":"2023-08-11","cited_by_count":18,"area":"lr"},{"id":"2405.14953","title":"MallowsPO: Fine-Tune Your LLM with Preference Dispersions","created":"2024-05-23","cited_by_count":18,"area":"alignment"},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2106.15078","title":"Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation","created":"2021-06-29","cited_by_count":17,"area":null},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16,"area":null},{"id":"2108.12472","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","created":"2021-08-27","cited_by_count":16,"area":null},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2204.02624","title":"There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory","created":"2022-04-06","cited_by_count":16,"area":null},{"id":"2206.00059","title":"A Mixture-of-Expert Approach to RL-based Dialogue Management","created":"2022-05-31","cited_by_count":16,"area":"moe"},{"id":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2307.03997","title":"Efficient Model-Free Exploration in Low-Rank MDPs","created":"2023-07-08","cited_by_count":16,"area":null},{"id":"2311.05195","title":"PRODIGy: a PROfile-based DIalogue Generation dataset","created":"2023-11-09","cited_by_count":16,"area":null},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2505.20417","title":"SCAR: Shapley Credit Assignment for More Efficient RLHF","created":"2025-05-26","cited_by_count":16,"area":"alignment"},{"id":"2101.02046","title":"TextBox: A Unified, Modularized, and Extensible Framework for Text Generation","created":"2021-01-06","cited_by_count":15,"area":null},{"id":"2105.08285","title":"Sublinear Least-Squares Value Iteration via Locality Sensitive Hashing","created":"2021-05-18","cited_by_count":15,"area":null},{"id":"2111.11133","title":"L-Verse: Bidirectional Generation Between Image and Text","created":"2021-11-22","cited_by_count":15,"area":null},{"id":"2308.02223","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","created":"2023-08-04","cited_by_count":15,"area":null}],"next_cursor":"100"}