{"total":322,"rows":[{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692,"area":null},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494,"area":null},{"id":"2106.01144","title":"Towards Emotional Support Dialog Systems","created":"2021-06-02","cited_by_count":299,"area":null},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"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":"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":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2410.15553","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","created":"2024-10-21","cited_by_count":102,"area":null},{"id":"2305.13711","title":"LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","created":"2023-05-23","cited_by_count":101,"area":null},{"id":"2309.02726","title":"Large Language Models for Automated Open-domain Scientific Hypotheses Discovery","created":"2023-09-06","cited_by_count":100,"area":null},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90,"area":null},{"id":"2109.05739","title":"CEM: Commonsense-aware Empathetic Response Generation","created":"2021-09-13","cited_by_count":89,"area":null},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"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":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","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":"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":"2208.11646","title":"Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation","created":"2022-08-24","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":"2212.07769","title":"CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models","created":"2022-12-15","cited_by_count":69,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"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":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2105.08920","title":"OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics","created":"2021-05-19","cited_by_count":61,"area":null},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59,"area":null},{"id":"2109.09707","title":"A Plug-and-Play Method for Controlled Text Generation","created":"2021-09-20","cited_by_count":56,"area":null},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56,"area":null},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2106.05555","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","created":"2021-06-10","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":"2312.15407","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":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2105.08316","title":"CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation","created":"2021-05-18","cited_by_count":42,"area":null},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2212.09235","title":"PAL: Persona-Augmented Emotional Support Conversation Generation","created":"2022-12-19","cited_by_count":39,"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":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2402.11975","title":"Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations","created":"2024-02-19","cited_by_count":36,"area":null},{"id":"2101.00939","title":"CRSLab: An Open-Source Toolkit for Building Conversational Recommender System","created":"2021-01-04","cited_by_count":34,"area":null},{"id":"2108.01547","title":"EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training","created":"2021-08-03","cited_by_count":34,"area":null},{"id":"2306.01985","title":"COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements","created":"2023-06-03","cited_by_count":34,"area":null},{"id":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"id":"2305.04147","title":"Controllable Mixed-Initiative Dialogue Generation through Prompting","created":"2023-05-06","cited_by_count":32,"area":null},{"id":"2104.09340","title":"Code Structure Guided Transformer for Source Code Summarization","created":"2021-04-19","cited_by_count":30,"area":null},{"id":"2105.06071","title":"Semi-Supervised Variational Reasoning for Medical Dialogue Generation","created":"2021-05-13","cited_by_count":30,"area":null},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30,"area":null},{"id":"2109.06427","title":"Commonsense-Focused Dialogues for Response Generation: An Empirical Study","created":"2021-09-14","cited_by_count":30,"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":"2305.11262","title":"CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models","created":"2023-05-18","cited_by_count":28,"area":null},{"id":"2202.13587","title":"Rethinking and Refining the Distinct Metric","created":"2022-02-28","cited_by_count":27,"area":null},{"id":"2210.12400","title":"Varifocal Question Generation for Fact-checking","created":"2022-10-22","cited_by_count":27,"area":null},{"id":"2204.09890","title":"Spurious Correlations in Reference-Free Evaluation of Text Generation","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2205.14727","title":"CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI","created":"2022-05-29","cited_by_count":26,"area":null},{"id":"2406.04291","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","created":"2024-06-06","cited_by_count":26,"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":"2212.04634","title":"Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey","created":"2022-12-09","cited_by_count":22,"area":null},{"id":"2106.00507","title":"Towards Quantifiable Dialogue Coherence Evaluation","created":"2021-06-01","cited_by_count":21,"area":null},{"id":"2106.03044","title":"Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2207.08087","title":"Automatic Context Pattern Generation for Entity Set Expansion","created":"2022-07-17","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":"2405.17974","title":"Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations","created":"2024-05-28","cited_by_count":20,"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":"2204.09149","title":"DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation","created":"2022-04-19","cited_by_count":19,"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":"2210.11715","title":"Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2305.02364","title":"PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives","created":"2023-05-03","cited_by_count":19,"area":null},{"id":"2308.16797","title":"Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation","created":"2023-08-31","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":"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":"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":"2208.08845","title":"CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","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":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2408.14622","title":"What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation","created":"2024-08-26","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":"2106.03635","title":"GTM: A Generative Triple-Wise Model for Conversational Question Generation","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2112.13556","title":"Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling","created":"2021-12-27","cited_by_count":16,"area":null},{"id":"2210.03884","title":"Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness","created":"2022-10-08","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":"2105.11696","title":"Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation","created":"2021-05-25","cited_by_count":15,"area":null},{"id":"2106.03816","title":"Diversity driven Query Rewriting in Search Advertising","created":"2021-06-07","cited_by_count":15,"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":"2205.13771","title":"IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2301.04907","title":"Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation","created":"2023-01-12","cited_by_count":14,"area":null},{"id":"2105.15171","title":"Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2112.07194","title":"MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation","created":"2021-12-14","cited_by_count":13,"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":"2205.10977","title":"What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveys","created":"2022-05-23","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}],"next_cursor":"100"}