{"total":434,"rows":[{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2408.04682","title":"ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities","created":"2024-08-08","cited_by_count":295,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"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":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180,"area":null},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2109.14739","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","created":"2021-09-29","cited_by_count":139,"area":null},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138,"area":null},{"id":"2305.14536","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","created":"2023-05-23","cited_by_count":131,"area":"lr"},{"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":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106,"area":null},{"id":"2111.14592","title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","created":"2021-11-29","cited_by_count":102,"area":null},{"id":"2109.07506","title":"Dialogue State Tracking with a Language Model using Schema-Driven Prompting","created":"2021-09-15","cited_by_count":94,"area":null},{"id":"2104.00773","title":"MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation","created":"2021-04-01","cited_by_count":88,"area":null},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75,"area":null},{"id":"2305.13040","title":"SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents","created":"2023-05-22","cited_by_count":71,"area":"agents"},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63,"area":null},{"id":"2405.08355","title":"Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark","created":"2024-05-14","cited_by_count":63,"area":"agents"},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63,"area":"lr"},{"id":"2105.04222","title":"Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking","created":"2021-05-10","cited_by_count":61,"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":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56,"area":null},{"id":"2304.06556","title":"Are LLMs All You Need for Task-Oriented Dialogue?","created":"2023-04-13","cited_by_count":54,"area":null},{"id":"2109.04655","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","created":"2021-09-10","cited_by_count":52,"area":null},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52,"area":null},{"id":"2201.08904","title":"Description-Driven Task-Oriented Dialog Modeling","created":"2022-01-21","cited_by_count":50,"area":null},{"id":"2308.06966","title":"EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce","created":"2023-08-14","cited_by_count":49,"area":null},{"id":"2506.09902","title":"PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants","created":"2025-06-11","cited_by_count":48,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2203.06654","title":"Continual Prompt Tuning for Dialog State Tracking","created":"2022-03-13","cited_by_count":44,"area":null},{"id":"2210.04185","title":"Controllable Dialogue Simulation with In-Context Learning","created":"2022-10-09","cited_by_count":42,"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":"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":"2402.15491","title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","created":"2024-02-23","cited_by_count":39,"area":"agents"},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2104.08524","title":"Multilingual and Cross-Lingual Intent Detection from Spoken Data","created":"2021-04-17","cited_by_count":35,"area":null},{"id":"2110.06800","title":"SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems","created":"2021-10-13","cited_by_count":34,"area":null},{"id":"2111.11894","title":"TWEETSUMM -- A Dialog Summarization Dataset for Customer Service","created":"2021-11-23","cited_by_count":34,"area":null},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34,"area":null},{"id":"2402.10466","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","created":"2024-02-16","cited_by_count":34,"area":"agents"},{"id":"2503.00564","title":"ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models","created":"2025-03-01","cited_by_count":34,"area":"agents"},{"id":"2306.09821","title":"Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System","created":"2023-06-16","cited_by_count":32,"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":"2110.07679","title":"GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems","created":"2021-10-14","cited_by_count":31,"area":null},{"id":"2105.14150","title":"Annotation Inconsistency and Entity Bias in MultiWOZ","created":"2021-05-29","cited_by_count":30,"area":null},{"id":"2109.04645","title":"CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2109.13489","title":"\"How Robust r u?\": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations","created":"2021-09-28","cited_by_count":30,"area":null},{"id":"2109.04137","title":"Fusing task-oriented and open-domain dialogues in conversational agents","created":"2021-09-09","cited_by_count":28,"area":null},{"id":"2209.06638","title":"SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding","created":"2022-09-14","cited_by_count":28,"area":null},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"area":null},{"id":"2308.09055","title":"Don't lose the message while paraphrasing: A study on content preserving style transfer","created":"2023-08-17","cited_by_count":25,"area":null},{"id":"2310.14970","title":"Towards LLM-driven Dialogue State Tracking","created":"2023-10-23","cited_by_count":25,"area":null},{"id":"2104.12714","title":"Focused Attention Improves Document-Grounded Generation","created":"2021-04-26","cited_by_count":24,"area":null},{"id":"2405.13037","title":"Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation","created":"2024-05-17","cited_by_count":24,"area":"agents"},{"id":"2410.19743","title":"AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2103.10518","title":"Pretraining the Noisy Channel Model for Task-Oriented Dialogue","created":"2021-03-18","cited_by_count":23,"area":null},{"id":"2201.13405","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","created":"2022-01-31","cited_by_count":23,"area":null},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23,"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":"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":"2410.14204","title":"MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations","created":"2024-10-18","cited_by_count":22,"area":null},{"id":"2102.02925","title":"Generalized Zero-shot Intent Detection via Commonsense Knowledge","created":"2021-02-04","cited_by_count":21,"area":null},{"id":"2110.08395","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","created":"2021-10-15","cited_by_count":21,"area":null},{"id":"2110.15659","title":"Amendable Generation for Dialogue State Tracking","created":"2021-10-29","cited_by_count":21,"area":null},{"id":"2507.20152","title":"Goal Alignment in LLM-Based User Simulators for Conversational AI","created":"2025-07-27","cited_by_count":21,"area":null},{"id":"2109.07263","title":"End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs","created":"2021-09-15","cited_by_count":20,"area":null},{"id":"2202.02912","title":"User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems","created":"2022-02-07","cited_by_count":20,"area":null},{"id":"2402.01828","title":"Retrieval Augmented End-to-End Spoken Dialog Models","created":"2024-02-02","cited_by_count":20,"area":"rag"},{"id":"2502.08820","title":"Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model","created":"2025-02-12","cited_by_count":20,"area":"agents"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2603.03116","title":"Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation","created":"2026-03-03","cited_by_count":20,"area":"agents"},{"id":"2110.08467","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2309.13233","title":"User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue","created":"2023-09-23","cited_by_count":19,"area":null},{"id":"2311.09758","title":"OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2403.12388","title":"Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models","created":"2024-03-19","cited_by_count":19,"area":null},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2204.06677","title":"Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking","created":"2022-04-14","cited_by_count":18,"area":null},{"id":"2204.07128","title":"Label Semantic Aware Pre-training for Few-shot Text Classification","created":"2022-04-14","cited_by_count":18,"area":null},{"id":"2207.14393","title":"LAD: Language Models as Data for Zero-Shot Dialog","created":"2022-07-28","cited_by_count":18,"area":null},{"id":"2308.10529","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","created":"2023-08-21","cited_by_count":18,"area":null},{"id":"2402.11633","title":"Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs","created":"2024-02-18","cited_by_count":18,"area":"synth"},{"id":"2408.09857","title":"TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation","created":"2024-08-19","cited_by_count":18,"area":null},{"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":"2205.13568","title":"Learning Dialogue Representations from Consecutive Utterances","created":"2022-05-26","cited_by_count":17,"area":null},{"id":"2402.02285","title":"SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking","created":"2024-02-03","cited_by_count":17,"area":"synth"},{"id":"2410.11710","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","created":"2024-10-15","cited_by_count":17,"area":null},{"id":"2505.20231","title":"MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents","created":"2025-05-26","cited_by_count":17,"area":"rag"},{"id":"2101.06779","title":"Few Shot Dialogue State Tracking using Meta-learning","created":"2021-01-17","cited_by_count":16,"area":null},{"id":"2204.04327","title":"Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue","created":"2022-04-08","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":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2202.03354","title":"Robust Dialogue State Tracking with Weak Supervision and Sparse Data","created":"2022-02-07","cited_by_count":15,"area":null},{"id":"2106.07056","title":"Schema-Guided Paradigm for Zero-Shot Dialog","created":"2021-06-13","cited_by_count":14,"area":null}],"next_cursor":"100"}