{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"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":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126},{"id":"1910.00292","title":"Generalization in Generation: A closer look at Exposure Bias","created":"2019-10-01","cited_by_count":123},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"1908.10090","title":"On NMT Search Errors and Model Errors: Cat Got Your Tongue?","created":"2019-08-27","cited_by_count":114},{"id":"1908.04734","title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","created":"2019-08-13","cited_by_count":108},{"id":"2204.01171","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","created":"2022-04-03","cited_by_count":108},{"id":"1709.08624","title":"Long Text Generation via Adversarial Training with Leaked Information","created":"2017-09-24","cited_by_count":100},{"id":"1511.05101","title":"How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?","created":"2015-11-16","cited_by_count":78},{"id":"1803.03453","title":"The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities","created":"2018-03-09","cited_by_count":78},{"id":"1804.06451","title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","created":"2018-04-17","cited_by_count":73},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64},{"id":"2002.02492","title":"Consistency of a Recurrent Language Model With Respect to Incomplete Decoding","created":"2020-02-06","cited_by_count":54},{"id":"2202.05148","title":"Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMET","created":"2022-02-10","cited_by_count":41},{"id":"2211.05826","title":"The CRINGE Loss: Learning what language not to model","created":"2022-11-10","cited_by_count":39},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38},{"id":"1608.07836","title":"What to do about non-standard (or non-canonical) language in NLP","created":"2016-08-28","cited_by_count":35},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33},{"id":"2010.04297","title":"Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task","created":"2020-10-08","cited_by_count":25},{"id":"1804.00361","title":"Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments","created":"2018-04-02","cited_by_count":19},{"id":"2109.08705","title":"Relating Neural Text Degeneration to Exposure Bias","created":"2021-09-17","cited_by_count":19},{"id":"2010.10245","title":"Human-Paraphrased References Improve Neural Machine Translation","created":"2020-10-20","cited_by_count":16},{"id":"2106.02278","title":"AgreeSum: Agreement-Oriented Multi-Document Summarization","created":"2021-06-04","cited_by_count":10},{"id":"2112.08914","title":"Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling","created":"2021-12-16","cited_by_count":10},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6},{"id":"2010.04379","title":"Q-learning with Language Model for Edit-based Unsupervised Summarization","created":"2020-10-09","cited_by_count":4},{"id":"2112.08670","title":"Amortized Noisy Channel Neural Machine Translation","created":"2021-12-16","cited_by_count":4},{"id":"2211.01471","title":"Dual Generator Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":1}],"next_cursor":null}