{"list":"other","total":56,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"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":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"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":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"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":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"1805.11080","title":"Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting","created":"2018-05-28","cited_by_count":158},{"id":"1802.08636","title":"Ranking Sentences for Extractive Summarization with Reinforcement Learning","created":"2018-02-23","cited_by_count":128},{"id":"2010.05478","title":"Evaluating Factuality in Generation with Dependency-level Entailment","created":"2020-10-12","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":"1909.02769","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","created":"2019-09-06","cited_by_count":118},{"id":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"1611.02796","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","created":"2016-11-09","cited_by_count":101},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96},{"id":"2010.05873","title":"Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data","created":"2020-10-12","cited_by_count":84},{"id":"1909.01214","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","created":"2019-09-03","cited_by_count":77},{"id":"1808.08866","title":"A Study of Reinforcement Learning for Neural Machine Translation","created":"2018-08-27","cited_by_count":74},{"id":"2107.06963","title":"Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features","created":"2021-07-14","cited_by_count":74},{"id":"1804.06451","title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","created":"2018-04-17","cited_by_count":73},{"id":"1804.07036","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","created":"2018-04-19","cited_by_count":64},{"id":"1902.02192","title":"Non-Monotonic Sequential Text Generation","created":"2019-02-05","cited_by_count":55},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55},{"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":"2205.07830","title":"FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization","created":"2022-05-16","cited_by_count":49},{"id":"1907.12894","title":"Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation","created":"2019-07-30","cited_by_count":14},{"id":"1904.02321","title":"Guiding Extractive Summarization with Question-Answering Rewards","created":"2019-04-04","cited_by_count":13},{"id":"2106.02278","title":"AgreeSum: Agreement-Oriented Multi-Document Summarization","created":"2021-06-04","cited_by_count":10}],"next_cursor":null}