{"list":"other","total":87,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"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":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"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":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2208.10264","title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","created":"2022-08-18","cited_by_count":515},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"2005.10200","title":"BERTweet: A pre-trained language model for English Tweets","created":"2020-05-20","cited_by_count":346},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"1602.05352","title":"Recommendations as Treatments: Debiasing Learning and Evaluation","created":"2016-02-17","cited_by_count":248},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"1906.06725","title":"Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good","created":"2019-06-16","cited_by_count":209},{"id":"2010.12472","title":"HateBERT: Retraining BERT for Abusive Language Detection in English","created":"2020-10-23","cited_by_count":207},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2112.01640","title":"MultiVerS: Improving scientific claim verification with weak supervision and full-document context","created":"2021-12-02","cited_by_count":143},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137},{"id":"1809.01984","title":"Training Millions of Personalized Dialogue Agents","created":"2018-09-06","cited_by_count":126},{"id":"1710.11214","title":"How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility","created":"2017-10-30","cited_by_count":120},{"id":"1901.05415","title":"Learning from Dialogue after Deployment: Feed Yourself, Chatbot!","created":"2019-01-16","cited_by_count":102},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93},{"id":"1905.10033","title":"Personalizing Dialogue Agents via Meta-Learning","created":"2019-05-24","cited_by_count":83},{"id":"2106.06169","title":"BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data","created":"2021-06-11","cited_by_count":75},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72},{"id":"1804.06512","title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","created":"2018-04-18","cited_by_count":53},{"id":"1909.00105","title":"Generating Personalized Recipes from Historical User Preferences","created":"2019-08-31","cited_by_count":53},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52},{"id":"1610.05461","title":"Personalized Machine Translation: Preserving Original Author Traits","created":"2016-10-18","cited_by_count":47},{"id":"2204.08128","title":"Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation","created":"2022-04-18","cited_by_count":47},{"id":"2003.07568","title":"XPersona: Evaluating Multilingual Personalized Chatbot","created":"2020-03-17","cited_by_count":36},{"id":"2101.06060","title":"The Challenge of Value Alignment: from Fairer Algorithms to AI Safety","created":"2021-01-15","cited_by_count":35},{"id":"2112.06346","title":"ValueNet: A New Dataset for Human Value Driven Dialogue System","created":"2021-12-12","cited_by_count":34},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32},{"id":"2106.04408","title":"HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation","created":"2021-06-08","cited_by_count":31},{"id":"2301.09656","title":"Selective Explanations: Leveraging Human Input to Align Explainable AI","created":"2023-01-23","cited_by_count":29},{"id":"2110.00135","title":"UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis","created":"2021-10-01","cited_by_count":28},{"id":"1805.01817","title":"Extreme Adaptation for Personalized Neural Machine Translation","created":"2018-05-04","cited_by_count":27},{"id":"1709.05467","title":"Acquiring Background Knowledge to Improve Moral Value Prediction","created":"2017-09-16","cited_by_count":22},{"id":"2205.00872","title":"COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas","created":"2022-05-02","cited_by_count":20},{"id":"1811.01990","title":"Compact Personalized Models for Neural Machine Translation","created":"2018-11-05","cited_by_count":19},{"id":"2204.07372","title":"A Personalized Dialogue Generator with Implicit User Persona Detection","created":"2022-04-15","cited_by_count":19},{"id":"1610.02891","title":"Personalizing a Dialogue System with Transfer Reinforcement Learning","created":"2016-10-10","cited_by_count":17},{"id":"2005.02431","title":"Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System","created":"2020-05-05","cited_by_count":16},{"id":"2106.02692","title":"The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity","created":"2021-06-04","cited_by_count":16},{"id":"2112.13556","title":"Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling","created":"2021-12-27","cited_by_count":16},{"id":"2204.07603","title":"Learning to Adapt Domain Shifts of Moral Values via Instance Weighting","created":"2022-04-15","cited_by_count":11},{"id":"1510.04267","title":"Debunking in a World of Tribes","created":"2015-10-14","cited_by_count":10},{"id":"2006.02964","title":"Personalizing Grammatical Error Correction: Adaptation to Proficiency Level and L1","created":"2020-06-04","cited_by_count":10},{"id":"1808.09658","title":"APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning","created":"2018-08-29","cited_by_count":9},{"id":"2206.05399","title":"Building a Personalized Dialogue System with Prompt-Tuning","created":"2022-06-11","cited_by_count":9},{"id":"2109.11136","title":"Non-Parametric Online Learning from Human Feedback for Neural Machine Translation","created":"2021-09-23","cited_by_count":8},{"id":"1908.00286","title":"Reinforcement Learning for Personalized Dialogue Management","created":"2019-08-01","cited_by_count":6},{"id":"2110.02148","title":"NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback","created":"2021-10-05","cited_by_count":5},{"id":"1905.00921","title":"Continuous Learning for Large-scale Personalized Domain Classification","created":"2019-05-02","cited_by_count":4},{"id":"2010.14342","title":"Listener's Social Identity Matters in Personalised Response Generation","created":"2020-10-27","cited_by_count":4},{"id":"2104.02667","title":"Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations","created":"2021-04-06","cited_by_count":4},{"id":"2005.12385","title":"Personalized Early Stage Alzheimer's Disease Detection: A Case Study of President Reagan's Speeches","created":"2020-05-08","cited_by_count":3},{"id":"2206.08446","title":"Methods for Estimating and Improving Robustness of Language Models","created":"2022-06-16","cited_by_count":3},{"id":"1812.07546","title":"Supervised Domain Enablement Attention for Personalized Domain Classification","created":"2018-12-18","cited_by_count":2}],"next_cursor":null}