{"list":"other","total":90,"rows":[{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2006.14779","title":"Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance","created":"2020-06-26","cited_by_count":399},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"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":"1312.3005","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","created":"2013-12-11","cited_by_count":308},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"1804.11283","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","created":"2018-04-30","cited_by_count":294},{"id":"2005.03754","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","created":"2020-05-07","cited_by_count":293},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"2201.06796","title":"CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities","created":"2022-01-18","cited_by_count":249},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"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":"2010.07079","title":"Recipes for Safety in Open-domain Chatbots","created":"2020-10-14","cited_by_count":170},{"id":"1905.05709","title":"Challenges in Building Intelligent Open-domain Dialog Systems","created":"2019-05-13","cited_by_count":147},{"id":"1711.04434","title":"Faithful to the Original: Fact Aware Neural Abstractive Summarization","created":"2017-11-13","cited_by_count":141},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"2104.04302","title":"Annotating and Modeling Fine-grained Factuality in Summarization","created":"2021-04-09","cited_by_count":131},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"1905.04071","title":"Survey on Evaluation Methods for Dialogue Systems","created":"2019-05-10","cited_by_count":126},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120},{"id":"2102.09130","title":"Entity-level Factual Consistency of Abstractive Text Summarization","created":"2021-02-18","cited_by_count":118},{"id":"1906.00080","title":"Gmail Smart Compose: Real-Time Assisted Writing","created":"2019-05-17","cited_by_count":98},{"id":"2011.06619","title":"Learning Latent Representations to Influence Multi-Agent Interaction","created":"2020-11-12","cited_by_count":93},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91},{"id":"1909.01214","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","created":"2019-09-03","cited_by_count":77},{"id":"2104.09061","title":"Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection","created":"2021-04-19","cited_by_count":76},{"id":"2004.14589","title":"Improved Natural Language Generation via Loss Truncation","created":"2020-04-30","cited_by_count":75},{"id":"2210.13669","title":"Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing","created":"2022-10-25","cited_by_count":71},{"id":"2211.05030","title":"Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers","created":"2022-11-09","cited_by_count":69},{"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":"2101.09157","title":"The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers","created":"2021-01-22","cited_by_count":61},{"id":"2010.01717","title":"STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation","created":"2020-10-04","cited_by_count":56},{"id":"2105.04623","title":"Improving Factual Consistency of Abstractive Summarization via Question Answering","created":"2021-05-10","cited_by_count":55},{"id":"2108.13684","title":"Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization","created":"2021-08-31","cited_by_count":51},{"id":"1907.10121","title":"SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python","created":"2019-07-23","cited_by_count":49},{"id":"2011.06486","title":"Overview of the Ninth Dialog System Technology Challenge: DSTC9","created":"2020-11-12","cited_by_count":49},{"id":"2103.06779","title":"MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding","created":"2021-03-11","cited_by_count":49},{"id":"2204.14146","title":"Training Language Models with Language Feedback","created":"2022-04-29","cited_by_count":49},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47},{"id":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43},{"id":"2201.04200","title":"The Turing Trap: The Promise & Peril of Human-Like Artificial Intelligence","created":"2022-01-11","cited_by_count":42},{"id":"1704.04572","title":"Task-Oriented Query Reformulation with Reinforcement Learning","created":"2017-04-15","cited_by_count":39},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36},{"id":"2005.03210","title":"Shared Autonomy with Learned Latent Actions","created":"2020-05-07","cited_by_count":34},{"id":"2106.01228","title":"Metaphor Generation with Conceptual Mappings","created":"2021-06-02","cited_by_count":32},{"id":"2203.05899","title":"Achieving Reliable Human Assessment of Open-Domain Dialogue Systems","created":"2022-03-11","cited_by_count":31},{"id":"2109.06427","title":"Commonsense-Focused Dialogues for Response Generation: An Empirical Study","created":"2021-09-14","cited_by_count":30},{"id":"2010.02140","title":"Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems","created":"2020-10-05","cited_by_count":26},{"id":"2008.12348","title":"Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations","created":"2020-08-27","cited_by_count":24},{"id":"2205.11930","title":"The Authenticity Gap in Human Evaluation","created":"2022-05-24","cited_by_count":24},{"id":"1810.06828","title":"The State of Speech in HCI: Trends, Themes and Challenges","created":"2018-10-16","cited_by_count":21},{"id":"2205.01825","title":"AmbiPun: Generating Humorous Puns with Ambiguous Context","created":"2022-05-04","cited_by_count":21},{"id":"1708.05122","title":"Evaluating Visual Conversational Agents via Cooperative Human-AI Games","created":"2017-08-17","cited_by_count":17},{"id":"2104.08620","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","created":"2021-04-17","cited_by_count":16},{"id":"2209.06321","title":"Alexa, Let's Work Together: Introducing the First Alexa Prize TaskBot Challenge on Conversational Task Assistance","created":"2022-09-13","cited_by_count":15},{"id":"1909.06283","title":"Toward Automated Quest Generation in Text-Adventure Games","created":"2019-09-13","cited_by_count":14},{"id":"2205.09665","title":"Automated Crossword Solving","created":"2022-05-19","cited_by_count":9},{"id":"1401.4597","title":"Dr.Fill: Crosswords and an Implemented Solver for Singly Weighted CSPs","created":"2014-01-18","cited_by_count":8},{"id":"2210.06470","title":"Who Wrote this? How Smart Replies Impact Language and Agency in the Workplace","created":"2022-10-07","cited_by_count":5},{"id":"2112.11911","title":"Towards Interactive Language Modeling","created":"2021-12-14","cited_by_count":4}],"next_cursor":null}