{"list":"other","total":99,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"2205.12615","title":"Autoformalization with Large Language Models","created":"2022-05-25","cited_by_count":263},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176},{"id":"2002.04108","title":"Adversarial Filters of Dataset Biases","created":"2020-02-10","cited_by_count":160},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"1906.06668","title":"Principles alone cannot guarantee ethical AI","created":"2019-06-16","cited_by_count":135},{"id":"2002.04833","title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","created":"2020-02-12","cited_by_count":120},{"id":"1912.01683","title":"Optimal Policies Tend to Seek Power","created":"2019-12-03","cited_by_count":119},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113},{"id":"2010.02559","title":"LEGAL-BERT: The Muppets straight out of Law School","created":"2020-10-06","cited_by_count":111},{"id":"2104.08762","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","created":"2021-04-18","cited_by_count":107},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105},{"id":"2104.13906","title":"Reward (Mis)design for Autonomous Driving","created":"2021-04-28","cited_by_count":104},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"2008.09094","title":"Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes","created":"2020-08-20","cited_by_count":101},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"1711.00482","title":"Learning with Latent Language","created":"2017-11-01","cited_by_count":75},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","cited_by_count":66},{"id":"1804.04268","title":"Incomplete Contracting and AI Alignment","created":"2018-04-12","cited_by_count":62},{"id":"2207.02200","title":"Offline RL Policies Should be Trained to be Adaptive","created":"2022-07-05","cited_by_count":52},{"id":"2204.02515","title":"Inferring Rewards from Language in Context","created":"2022-04-05","cited_by_count":50},{"id":"1906.09624","title":"On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference","created":"2019-06-23","cited_by_count":49},{"id":"2204.14146","title":"Training Language Models with Language Feedback","created":"2022-04-29","cited_by_count":49},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45},{"id":"2208.04347","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","created":"2022-08-08","cited_by_count":43},{"id":"1912.05652","title":"Learning Human Objectives by Evaluating Hypothetical Behavior","created":"2019-12-05","cited_by_count":41},{"id":"2009.14715","title":"Learning Rewards from Linguistic Feedback","created":"2020-09-30","cited_by_count":41},{"id":"2208.08489","title":"Understanding Scaling Laws for Recommendation Models","created":"2022-08-17","cited_by_count":38},{"id":"1707.06354","title":"Pragmatic-Pedagogic Value Alignment","created":"2017-07-20","cited_by_count":36},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36},{"id":"2111.14377","title":"Collective Intelligence for Deep Learning: A Survey of Recent Developments","created":"2021-11-29","cited_by_count":34},{"id":"1911.03872","title":"Location Attention for Extrapolation to Longer Sequences","created":"2019-11-10","cited_by_count":33},{"id":"2106.06613","title":"A New Formalism, Method and Open Issues for Zero-Shot Coordination","created":"2021-06-11","cited_by_count":33},{"id":"2010.07877","title":"Avoiding Side Effects By Considering Future Tasks","created":"2020-10-15","cited_by_count":32},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32},{"id":"2010.03538","title":"Exploring the Role of Argument Structure in Online Debate Persuasion","created":"2020-10-07","cited_by_count":26},{"id":"2006.06547","title":"Avoiding Side Effects in Complex Environments","created":"2020-06-11","cited_by_count":24},{"id":"2111.04158","title":"A Word on Machine Ethics: A Response to Jiang et al. (2021)","created":"2021-11-07","cited_by_count":23},{"id":"2105.07903","title":"Factoring Statutory Reasoning as Language Understanding Challenges","created":"2021-05-17","cited_by_count":20},{"id":"2102.09364","title":"Ethics as a service: a pragmatic operationalisation of AI Ethics","created":"2021-02-11","cited_by_count":19},{"id":"2202.01327","title":"Adaptive Sampling Strategies to Construct Equitable Training Datasets","created":"2022-01-31","cited_by_count":18},{"id":"2006.04734","title":"Reinforcement Learning Under Moral Uncertainty","created":"2020-06-08","cited_by_count":16},{"id":"1811.01267","title":"Legible Normativity for AI Alignment: The Value of Silly Rules","created":"2018-11-03","cited_by_count":15},{"id":"2005.07646","title":"Complex Societies and the Growth of the Law","created":"2020-05-15","cited_by_count":12},{"id":"2105.01044","title":"Goldilocks: Just-Right Tuning of BERT for Technology-Assisted Review","created":"2021-05-03","cited_by_count":12},{"id":"2104.12133","title":"What About the Precedent: An Information-Theoretic Analysis of Common Law","created":"2021-04-25","cited_by_count":11},{"id":"2101.05786","title":"Persuasive Natural Language Generation -- A Literature Review","created":"2021-01-14","cited_by_count":10},{"id":"2106.10394","title":"Uncertain Decisions Facilitate Better Preference Learning","created":"2021-06-19","cited_by_count":10},{"id":"2111.07158","title":"Robust Deep Reinforcement Learning for Extractive Legal Summarization","created":"2021-11-13","cited_by_count":10},{"id":"2208.08201","title":"Understanding Long Documents with Different Position-Aware Attentions","created":"2022-08-17","cited_by_count":7},{"id":"2204.05091","title":"Linguistic communication as (inverse) reward design","created":"2022-04-11","cited_by_count":6},{"id":"2206.06960","title":"ABCinML: Anticipatory Bias Correction in Machine Learning Applications","created":"2022-06-14","cited_by_count":6},{"id":"2109.00608","title":"An unsupervised framework for tracing textual sources of moral change","created":"2021-09-01","cited_by_count":4},{"id":"2201.11441","title":"Human-centered mechanism design with Democratic AI","created":"2022-01-27","cited_by_count":3},{"id":"1609.06616","title":"Gov2Vec: Learning Distributed Representations of Institutions and Their Legal Text","created":"2016-09-21","cited_by_count":1}],"next_cursor":null}