{"total":117,"rows":[{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441,"area":null},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376,"area":null},{"id":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"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":"2205.06537","title":"Productivity Assessment of Neural Code Completion","created":"2022-05-13","cited_by_count":98,"area":null},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90,"area":null},{"id":"2308.11995","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","created":"2023-08-23","cited_by_count":89,"area":null},{"id":"2203.13560","title":"MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation","created":"2022-03-25","cited_by_count":85,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"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":"2107.06963","title":"Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features","created":"2021-07-14","cited_by_count":74,"area":null},{"id":"2109.05794","title":"Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions","created":"2021-09-13","cited_by_count":63,"area":null},{"id":"2201.04723","title":"Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents","created":"2022-01-12","cited_by_count":62,"area":null},{"id":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60,"area":null},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59,"area":null},{"id":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56,"area":null},{"id":"2212.09739","title":"LENS: A Learnable Evaluation Metric for Text Simplification","created":"2022-12-19","cited_by_count":54,"area":null},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2301.05843","title":"Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data","created":"2023-01-14","cited_by_count":48,"area":null},{"id":"2312.15407","title":"A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators","created":"2023-12-24","cited_by_count":45,"area":null},{"id":"2106.01625","title":"Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech","created":"2021-06-03","cited_by_count":42,"area":null},{"id":"2104.06828","title":"Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge","created":"2021-04-14","cited_by_count":40,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2112.00791","title":"Controlling Conditional Language Models without Catastrophic Forgetting","created":"2021-12-01","cited_by_count":32,"area":null},{"id":"2205.01497","title":"Semantic Diversity in Dialogue with Natural Language Inference","created":"2022-05-03","cited_by_count":29,"area":null},{"id":"2303.17574","title":"Elastic Weight Removal for Faithful and Abstractive Dialogue Generation","created":"2023-03-30","cited_by_count":29,"area":null},{"id":"2111.02110","title":"Automatic Evaluation and Moderation of Open-domain Dialogue Systems","created":"2021-11-03","cited_by_count":28,"area":null},{"id":"2108.05271","title":"DeliData: A dataset for deliberation in multi-party problem solving","created":"2021-08-11","cited_by_count":26,"area":null},{"id":"2204.08046","title":"Evaluating Mixed-initiative Conversational Search Systems via User Simulation","created":"2022-04-17","cited_by_count":25,"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":"2408.13545","title":"IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering","created":"2024-08-24","cited_by_count":19,"area":null},{"id":"2205.02517","title":"A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration","created":"2022-05-05","cited_by_count":18,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2409.02413","title":"Abstractive Text Summarization: State of the Art, Challenges, and Improvements","created":"2024-09-04","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":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16,"area":null},{"id":"2305.08566","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","created":"2023-05-15","cited_by_count":16,"area":null},{"id":"2405.02178","title":"Assessing and Verifying Task Utility in LLM-Powered Applications","created":"2024-05-03","cited_by_count":16,"area":null},{"id":"2109.06471","title":"Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization","created":"2021-09-14","cited_by_count":15,"area":null},{"id":"2210.13832","title":"FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation","created":"2022-10-25","cited_by_count":13,"area":null},{"id":"2304.09866","title":"Towards Designing a ChatGPT Conversational Companion for Elderly People","created":"2023-04-18","cited_by_count":13,"area":null},{"id":"2310.08958","title":"xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark","created":"2023-10-13","cited_by_count":13,"area":null},{"id":"2203.07657","title":"Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2102.02191","title":"DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation","created":"2021-02-03","cited_by_count":10,"area":null},{"id":"2109.12211","title":"Style Control for Schema-Guided Natural Language Generation","created":"2021-09-24","cited_by_count":10,"area":null},{"id":"2203.06063","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2306.12794","title":"Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4","created":"2023-06-22","cited_by_count":10,"area":null},{"id":"2407.03841","title":"On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation","created":"2024-07-04","cited_by_count":10,"area":null},{"id":"2503.01513","title":"Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2410.02503","title":"Mixed-Session Conversation with Egocentric Memory","created":"2024-10-03","cited_by_count":8,"area":null},{"id":"2103.15335","title":"Changing the Mind of Transformers for Topically-Controllable Language Generation","created":"2021-03-29","cited_by_count":7,"area":null},{"id":"2106.06528","title":"Local Explanation of Dialogue Response Generation","created":"2021-06-11","cited_by_count":7,"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":"2205.12502","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2210.03167","title":"FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2105.11197","title":"Towards Standard Criteria for human evaluation of Chatbots: A Survey","created":"2021-05-24","cited_by_count":6,"area":null},{"id":"2106.14614","title":"Progressive Open-Domain Response Generation with Multiple Controllable Attributes","created":"2021-06-07","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":"2505.11665","title":"Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2106.06411","title":"Zero-Shot Controlled Generation with Encoder-Decoder Transformers","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2109.01958","title":"SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks","created":"2021-09-05","cited_by_count":5,"area":null},{"id":"2109.06717","title":"Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2112.08657","title":"Taming Repetition in Dialogue Generation","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2206.09403","title":"MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue","created":"2022-06-19","cited_by_count":5,"area":null},{"id":"2202.06633","title":"FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2210.12461","title":"Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2301.13372","title":"Improving Open-Domain Dialogue Evaluation with a Causal Inference Model","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2306.10452","title":"MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2306.13460","title":"Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation","created":"2023-06-23","cited_by_count":4,"area":null},{"id":"2307.14440","title":"Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2311.13910","title":"Dialogue Quality and Emotion Annotations for Customer Support Conversations","created":"2023-11-23","cited_by_count":4,"area":null},{"id":"2404.15894","title":"Assessing The Potential Of Mid-Sized Language Models For Clinical QA","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2406.15000","title":"Unveiling the Impact of Multi-Modal Interactions on User Engagement: A Comprehensive Evaluation in AI-driven Conversations","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2503.03532","title":"AI-Enabled Conversational Journaling for Advancing Parkinson's Disease Symptom Tracking","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"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":"2306.03984","title":"Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2306.14696","title":"How About Kind of Generating Hedges using End-to-End Neural Models?","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2406.11228","title":"ComperDial: Commonsense Persona-grounded Dialogue Dataset and Benchmark","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2603.02876","title":"Eval4Sim: An Evaluation Framework for Persona Simulation","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2101.01334","title":"Evaluating Empathetic Chatbots in Customer Service Settings","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2103.11151","title":"The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues","created":"2021-03-20","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":"2204.05805","title":"Learning to Express in Knowledge-Grounded Conversation","created":"2022-04-12","cited_by_count":2,"area":null},{"id":"2205.11206","title":"Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learning","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2302.05406","title":"Adversarial Transformer Language Models for Contextual Commonsense Inference","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2308.06502","title":"Three Ways of Using Large Language Models to Evaluate Chat","created":"2023-08-12","cited_by_count":2,"area":null},{"id":"2308.14115","title":"Situated Natural Language Explanations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2512.10918","title":"CompanionCast: Toward Social Collaboration with Multi-Agent Systems in Shared Experiences","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2104.05277","title":"Building a Swedish Open-Domain Conversational Language Model","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2107.07771","title":"Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2304.00884","title":"Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation","created":"2023-04-03","cited_by_count":1,"area":null},{"id":"2304.02812","title":"Pragmatically Appropriate Diversity for Dialogue Evaluation","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2308.06095","title":"Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes","created":"2023-08-11","cited_by_count":1,"area":null},{"id":"2310.00410","title":"Open-Domain Dialogue Quality Evaluation: Deriving Nugget-level Scores from Turn-level Scores","created":"2023-09-30","cited_by_count":1,"area":null}],"next_cursor":"100"}