{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"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":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"1606.03126","title":"Key-Value Memory Networks for Directly Reading Documents","created":"2016-06-09","cited_by_count":223},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"1507.04808","title":"Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models","created":"2015-07-17","cited_by_count":207},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198},{"id":"2005.00456","title":"USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation","created":"2020-05-01","cited_by_count":188},{"id":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168},{"id":"2006.12719","title":"Unsupervised Evaluation of Interactive Dialog with DialoGPT","created":"2020-06-23","cited_by_count":139},{"id":"1503.02364","title":"Neural Responding Machine for Short-Text Conversation","created":"2015-03-09","cited_by_count":124},{"id":"2306.07899","title":"Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks","created":"2023-06-13","cited_by_count":103},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90},{"id":"2308.11995","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","created":"2023-08-23","cited_by_count":89},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73},{"id":"2302.03269","title":"PLACES: Prompting Language Models for Social Conversation Synthesis","created":"2023-02-07","cited_by_count":72},{"id":"2012.13391","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","created":"2020-12-24","cited_by_count":68},{"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},{"id":"2009.11321","title":"Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining","created":"2020-09-23","cited_by_count":59},{"id":"2011.00483","title":"Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems","created":"2020-11-01","cited_by_count":47},{"id":"2305.12947","title":"ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness","created":"2023-05-22","cited_by_count":41},{"id":"2402.16795","title":"If in a Crowdsourced Data Annotation Pipeline, a GPT-4","created":"2024-02-26","cited_by_count":38},{"id":"2111.02110","title":"Automatic Evaluation and Moderation of Open-domain Dialogue Systems","created":"2021-11-03","cited_by_count":28},{"id":"2212.09246","title":"I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation","created":"2022-12-19","cited_by_count":21},{"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},{"id":"2009.04617","title":"Emora: An Inquisitive Social Chatbot Who Cares For You","created":"2020-09-10","cited_by_count":16},{"id":"2309.06490","title":"Leveraging Large Language Models for Automated Dialogue Analysis","created":"2023-09-12","cited_by_count":14},{"id":"2310.08958","title":"xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark","created":"2023-10-13","cited_by_count":13},{"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},{"id":"2407.03841","title":"On the Benchmarking of LLMs for Open-Domain Dialogue Evaluation","created":"2024-07-04","cited_by_count":10},{"id":"2310.15758","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","created":"2023-10-24","cited_by_count":7},{"id":"2407.11660","title":"ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues","created":"2024-07-16","cited_by_count":5}],"next_cursor":null}