{"list":"other","total":51,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2302.14520","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","created":"2023-02-28","cited_by_count":420},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1707.06875","title":"Why We Need New Evaluation Metrics for NLG","created":"2017-07-21","cited_by_count":233},{"id":"2209.06243","title":"CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task","created":"2022-09-13","cited_by_count":207},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163},{"id":"2004.00646","title":"A Survey on Conversational Recommender Systems","created":"2020-04-01","cited_by_count":143},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"2109.06835","title":"The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation","created":"2021-09-14","cited_by_count":97},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90},{"id":"2309.11925","title":"Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task","created":"2023-09-21","cited_by_count":88},{"id":"1810.05995","title":"BLEU is Not Suitable for the Evaluation of Text Simplification","created":"2018-10-14","cited_by_count":78},{"id":"2003.07490","title":"Recent Advances and Challenges in Task-oriented Dialog System","created":"2020-03-17","cited_by_count":78},{"id":"2305.02750","title":"A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects","created":"2023-05-04","cited_by_count":66},{"id":"1904.02743","title":"How should my chatbot interact? A survey on human-chatbot interaction design","created":"2019-04-04","cited_by_count":56},{"id":"2201.10474","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","created":"2022-01-25","cited_by_count":53},{"id":"2008.02311","title":"Conceptual Metaphors Impact Perceptions of Human-AI Collaboration","created":"2020-08-05","cited_by_count":47},{"id":"2105.03748","title":"Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems","created":"2021-05-08","cited_by_count":47},{"id":"2007.04792","title":"Targeting the Benchmark: On Methodology in Current Natural Language Processing Research","created":"2020-07-07","cited_by_count":45},{"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},{"id":"2104.12871","title":"Why AI is Harder Than We Think","created":"2021-04-26","cited_by_count":41},{"id":"2012.14666","title":"RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems","created":"2020-12-29","cited_by_count":36},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36},{"id":"2006.06110","title":"Towards Unified Dialogue System Evaluation: A Comprehensive Analysis of Current Evaluation Protocols","created":"2020-06-10","cited_by_count":35},{"id":"2204.00447","title":"Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation","created":"2022-04-01","cited_by_count":33},{"id":"2201.06657","title":"A Literature Survey of Recent Advances in Chatbots","created":"2022-01-17","cited_by_count":26},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26},{"id":"2103.06944","title":"Preregistering NLP Research","created":"2021-03-11","cited_by_count":25},{"id":"2105.03311","title":"Translation Quality Assessment: A Brief Survey on Manual and Automatic Methods","created":"2021-05-05","cited_by_count":23},{"id":"2310.19792","title":"The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics","created":"2023-10-30","cited_by_count":23},{"id":"2106.00507","title":"Towards Quantifiable Dialogue Coherence Evaluation","created":"2021-06-01","cited_by_count":21},{"id":"2305.01633","title":"Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP","created":"2023-05-02","cited_by_count":21},{"id":"2012.15375","title":"Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration","created":"2020-12-31","cited_by_count":20},{"id":"2005.07362","title":"Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation","created":"2020-05-15","cited_by_count":19},{"id":"2108.01182","title":"Underreporting of errors in NLG output, and what to do about it","created":"2021-08-02","cited_by_count":19},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","cited_by_count":12},{"id":"2106.10901","title":"Software-Based Dialogue Systems: Survey, Taxonomy and Challenges","created":"2021-06-21","cited_by_count":11},{"id":"2302.07406","title":"Conversational AI-Powered Design: ChatGPT as Designer, User, and Product","created":"2023-02-15","cited_by_count":8},{"id":"2210.08692","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","created":"2022-10-17","cited_by_count":6},{"id":"1707.05470","title":"DeepProbe: Information Directed Sequence Understanding and Chatbot Design via Recurrent Neural Networks","created":"2017-07-18","cited_by_count":4},{"id":"2111.00572","title":"What Went Wrong? Explaining Overall Dialogue Quality through Utterance-Level Impacts","created":"2021-10-31","cited_by_count":2}],"next_cursor":null}