{"total":139,"rows":[{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692,"area":null},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"area":null},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132,"area":null},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2308.11995","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","created":"2023-08-23","cited_by_count":89,"area":null},{"id":"2205.07540","title":"The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialogues","created":"2022-05-16","cited_by_count":79,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2103.15721","title":"CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems","created":"2021-03-29","cited_by_count":62,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"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,"area":null},{"id":"2310.13420","title":"Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations","created":"2023-10-20","cited_by_count":47,"area":null},{"id":"2312.10007","title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","created":"2023-12-15","cited_by_count":47,"area":null},{"id":"2109.08828","title":"Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes","created":"2021-09-18","cited_by_count":43,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"area":null},{"id":"2211.05826","title":"The CRINGE Loss: Learning what language not to model","created":"2022-11-10","cited_by_count":39,"area":null},{"id":"2104.07081","title":"TWEAC: Transformer with Extendable QA Agent Classifiers","created":"2021-04-14","cited_by_count":37,"area":null},{"id":"2108.13134","title":"Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation","created":"2021-08-30","cited_by_count":37,"area":null},{"id":"2110.07518","title":"SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures","created":"2021-10-14","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":"2104.08728","title":"Revealing Persona Biases in Dialogue Systems","created":"2021-04-18","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":"2301.09919","title":"Opportunities and Challenges in Neural Dialog Tutoring","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2111.05204","title":"Reason first, then respond: Modular Generation for Knowledge-infused Dialogue","created":"2021-11-09","cited_by_count":32,"area":null},{"id":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2106.00874","title":"Conversational Question Answering: A Survey","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2305.17878","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","created":"2023-05-29","cited_by_count":31,"area":"lr"},{"id":"2307.02768","title":"Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts","created":"2023-07-06","cited_by_count":31,"area":"lr"},{"id":"2308.06212","title":"A Large Language Model Enhanced Conversational Recommender System","created":"2023-08-11","cited_by_count":31,"area":null},{"id":"2204.03025","title":"Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment","created":"2022-04-06","cited_by_count":25,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2309.04344","title":"Zero-Shot Robustification of Zero-Shot Models","created":"2023-09-08","cited_by_count":24,"area":null},{"id":"2112.05843","title":"Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity","created":"2021-12-10","cited_by_count":22,"area":null},{"id":"2211.09267","title":"Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality","created":"2022-11-16","cited_by_count":22,"area":null},{"id":"2211.17148","title":"ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format","created":"2022-11-30","cited_by_count":22,"area":null},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22,"area":null},{"id":"2506.10150","title":"When Large Language Models are Reliable for Judging Empathic Communication","created":"2025-06-11","cited_by_count":21,"area":null},{"id":"2205.00872","title":"COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas","created":"2022-05-02","cited_by_count":20,"area":null},{"id":"2109.04096","title":"A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2112.08812","title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","created":"2021-12-16","cited_by_count":19,"area":null},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","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":"2105.02573","title":"Assessing Dialogue Systems with Distribution Distances","created":"2021-05-06","cited_by_count":16,"area":null},{"id":"2204.10591","title":"SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues","created":"2022-04-22","cited_by_count":16,"area":null},{"id":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16,"area":null},{"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":"2112.01922","title":"MetaQA: Combining Expert Agents for Multi-Skill Question Answering","created":"2021-12-03","cited_by_count":15,"area":null},{"id":"2305.10195","title":"Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy","created":"2023-05-17","cited_by_count":15,"area":null},{"id":"2208.08110","title":"PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2411.07213","title":"Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2212.08195","title":"Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines","created":"2022-12-15","cited_by_count":13,"area":"lr"},{"id":"2306.17674","title":"X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents","created":"2023-06-30","cited_by_count":13,"area":null},{"id":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2105.01992","title":"LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing","created":"2021-05-05","cited_by_count":11,"area":null},{"id":"2311.04694","title":"Evaluating Generative Ad Hoc Information Retrieval","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2109.07713","title":"Transferable Persona-Grounded Dialogues via Grounded Minimal Edits","created":"2021-09-16","cited_by_count":10,"area":null},{"id":"2211.01587","title":"Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2110.08345","title":"Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction","created":"2021-10-15","cited_by_count":9,"area":null},{"id":"2112.08321","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","created":"2021-12-15","cited_by_count":9,"area":null},{"id":"2212.09180","title":"Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems","created":"2022-12-18","cited_by_count":9,"area":null},{"id":"2301.09412","title":"Deep Learning Mental Health Dialogue System","created":"2023-01-23","cited_by_count":9,"area":null},{"id":"2305.00034","title":"Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation","created":"2023-04-28","cited_by_count":9,"area":null},{"id":"2102.10952","title":"A Relational Tsetlin Machine with Applications to Natural Language Understanding","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2109.12702","title":"Extracting and Inferring Personal Attributes from Dialogue","created":"2021-09-26","cited_by_count":8,"area":null},{"id":"2110.11205","title":"Robustness through Data Augmentation Loss Consistency","created":"2021-10-21","cited_by_count":8,"area":null},{"id":"2304.11220","title":"Learn What NOT to Learn: Towards Generative Safety in Chatbots","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2404.01399","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","created":"2024-04-01","cited_by_count":8,"area":null},{"id":"2202.01155","title":"The slurk Interaction Server Framework: Better Data for Better Dialog Models","created":"2022-02-02","cited_by_count":7,"area":null},{"id":"2301.05154","title":"Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2302.07926","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","created":"2023-02-15","cited_by_count":7,"area":"lr"},{"id":"2305.17280","title":"Improved Instruction Ordering in Recipe-Grounded Conversation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2306.10317","title":"Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation","created":"2023-06-17","cited_by_count":7,"area":null},{"id":"2110.06905","title":"Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue","created":"2021-10-13","cited_by_count":6,"area":null},{"id":"2203.12187","title":"Converse: A Tree-Based Modular Task-Oriented Dialogue System","created":"2022-03-23","cited_by_count":6,"area":null},{"id":"2207.12551","title":"DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkit","created":"2022-07-25","cited_by_count":6,"area":null},{"id":"2210.12362","title":"EnDex: Evaluation of Dialogue Engagingness at Scale","created":"2022-10-22","cited_by_count":6,"area":null},{"id":"2212.06564","title":"Prescriptive Process Monitoring in Intelligent Process Automation with Chatbot Orchestration","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2302.06598","title":"Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2304.14318","title":"q2d: Turning Questions into Dialogs to Teach Models How to Search","created":"2023-04-27","cited_by_count":5,"area":null},{"id":"2108.12582","title":"Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation","created":"2021-08-28","cited_by_count":4,"area":null},{"id":"2207.12021","title":"Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2403.07910","title":"MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressions","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2410.22370","title":"Survey of User Interface Design and Interaction Techniques in Generative AI Applications","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2105.00825","title":"DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2112.06723","title":"Understanding and Improving the Exemplar-based Generation for Open-domain Conversation","created":"2021-12-13","cited_by_count":3,"area":null},{"id":"2205.02570","title":"Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation","created":"2022-05-05","cited_by_count":3,"area":null},{"id":"2211.13560","title":"How \"open\" are the conversations with open-domain chatbots? A proposal for Speech Event based evaluation","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2212.01739","title":"KPT: Keyword-guided Pre-training for Grounded Dialog Generation","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2212.13005","title":"TextBox 2.0: A Text Generation Library with Pre-trained Language Models","created":"2022-12-26","cited_by_count":3,"area":null},{"id":"2306.03866","title":"Correction of Errors in Preference Ratings from Automated Metrics for Text Generation","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2310.00892","title":"No Offense Taken: Eliciting Offensiveness from Language Models","created":"2023-10-02","cited_by_count":3,"area":"safety"},{"id":"2506.10622","title":"SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation","created":"2025-06-12","cited_by_count":3,"area":"agents"},{"id":"2101.01334","title":"Evaluating Empathetic Chatbots in Customer Service Settings","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2108.01369","title":"How to Evaluate Your Dialogue Models: A Review of Approaches","created":"2021-08-03","cited_by_count":2,"area":null},{"id":"2108.11063","title":"Viola: A Topic Agnostic Generate-and-Rank Dialogue System","created":"2021-08-25","cited_by_count":2,"area":null}],"next_cursor":"100"}