{"total":48,"rows":[{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2104.08667","title":"SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations","created":"2021-04-18","cited_by_count":56,"area":null},{"id":"2206.11309","title":"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog","created":"2022-06-22","cited_by_count":51,"area":null},{"id":"2305.09067","title":"SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting","created":"2023-05-15","cited_by_count":39,"area":null},{"id":"2306.01386","title":"ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?","created":"2023-06-02","cited_by_count":38,"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":"2102.05126","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","created":"2021-02-09","cited_by_count":31,"area":null},{"id":"2205.10400","title":"Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog","created":"2022-05-20","cited_by_count":30,"area":null},{"id":"2311.08788","title":"X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2203.09711","title":"DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2207.14627","title":"\"Do you follow me?\": A Survey of Recent Approaches in Dialogue State Tracking","created":"2022-07-29","cited_by_count":22,"area":null},{"id":"2203.13927","title":"What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation","created":"2022-03-25","cited_by_count":18,"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":"2203.10012","title":"Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges","created":"2022-03-18","cited_by_count":13,"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":"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":"2304.05253","title":"Approximating Online Human Evaluation of Social Chatbots with Prompting","created":"2023-04-11","cited_by_count":11,"area":null},{"id":"2111.02574","title":"Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues","created":"2021-11-04","cited_by_count":10,"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":"2201.06849","title":"Toward Self-learning End-to-End Task-Oriented Dialog Systems","created":"2022-01-18","cited_by_count":9,"area":null},{"id":"2207.14403","title":"Interactive Evaluation of Dialog Track at DSTC9","created":"2022-07-28","cited_by_count":9,"area":null},{"id":"2305.13690","title":"Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2205.00965","title":"State-of-the-art in Open-domain Conversational AI: A Survey","created":"2022-05-02","cited_by_count":5,"area":null},{"id":"2207.12185","title":"Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning","created":"2022-07-25","cited_by_count":5,"area":null},{"id":"2208.10448","title":"Dialogue Term Extraction using Transfer Learning and Topological Data Analysis","created":"2022-08-22","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":"2302.09424","title":"Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation","created":"2023-02-18","cited_by_count":4,"area":null},{"id":"2110.11514","title":"SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching","created":"2021-10-21","cited_by_count":3,"area":null},{"id":"2111.08808","title":"User Response and Sentiment Prediction for Automatic Dialogue Evaluation","created":"2021-11-16","cited_by_count":3,"area":null},{"id":"2209.00876","title":"Dialogue Evaluation with Offline Reinforcement Learning","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2212.05373","title":"Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access","created":"2022-12-10","cited_by_count":3,"area":null},{"id":"2212.08992","title":"PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment","created":"2022-12-18","cited_by_count":3,"area":null},{"id":"2204.13496","title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","created":"2022-04-28","cited_by_count":2,"area":null},{"id":"2206.08723","title":"CookDial: A dataset for task-oriented dialogs grounded in procedural documents","created":"2022-06-17","cited_by_count":2,"area":null},{"id":"2208.08094","title":"SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation","created":"2022-08-17","cited_by_count":2,"area":null},{"id":"2209.11746","title":"Evaluating Agent Interactions Through Episodic Knowledge Graphs","created":"2022-09-22","cited_by_count":2,"area":null},{"id":"2306.11879","title":"Open-Domain Text Evaluation via Contrastive Distribution Methods","created":"2023-06-20","cited_by_count":1,"area":null},{"id":"2309.05680","title":"Evaluating Chatbots to Promote Users' Trust -- Practices and Open Problems","created":"2023-09-09","cited_by_count":1,"area":null},{"id":"2101.07947","title":"WeChat AI & ICT's Submission for DSTC9 Interactive Dialogue Evaluation Track","created":"2021-01-20","cited_by_count":0,"area":null},{"id":"2103.05561","title":"Did Chatbots Miss Their 'Apollo Moment'? A Survey of the Potential, Gaps and Lessons from Using Collaboration Assistants During COVID-19","created":"2021-02-27","cited_by_count":0,"area":null},{"id":"2106.14433","title":"Efficient Dialogue State Tracking by Masked Hierarchical Transformer","created":"2021-06-28","cited_by_count":0,"area":null},{"id":"2112.12318","title":"Investigating Effect of Dialogue History in Multilingual Task Oriented Dialogue Systems","created":"2021-12-23","cited_by_count":0,"area":null},{"id":"2203.07742","title":"ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2208.10918","title":"The DialPort tools","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2305.18212","title":"Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2308.01887","title":"Athena 2.0: Discourse and User Modeling in Open Domain Dialogue","created":"2023-08-03","cited_by_count":0,"area":null},{"id":"2409.07823","title":"Online vs Offline: A Comparative Study of First-Party and Third-Party Evaluations of Social Chatbots","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2410.18430","title":"Building Dialogue Understanding Models for Low-resource Language Indonesian from Scratch","created":"2024-10-24","cited_by_count":0,"area":null}],"next_cursor":null}