{"total":58,"rows":[{"id":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429,"area":"safety"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2402.16187","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","created":"2024-02-25","cited_by_count":50,"area":"safety"},{"id":"2101.10579","title":"Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs","created":"2021-01-26","cited_by_count":45,"area":null},{"id":"2403.14541","title":"EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling","created":"2024-03-21","cited_by_count":45,"area":null},{"id":"2106.08942","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","created":"2021-06-16","cited_by_count":33,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30,"area":null},{"id":"2202.08159","title":"Domain Adaptive Fake News Detection via Reinforcement Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2202.00535","title":"Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning","created":"2022-02-01","cited_by_count":25,"area":"rag"},{"id":"2211.03468","title":"Generative Transformers for Design Concept Generation","created":"2022-11-07","cited_by_count":21,"area":null},{"id":"2106.04681","title":"Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection","created":"2021-05-25","cited_by_count":20,"area":null},{"id":"2109.15144","title":"A Review of Text Style Transfer using Deep Learning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2111.08489","title":"Generative Pre-Trained Transformer for Design Concept Generation: An Exploration","created":"2021-11-16","cited_by_count":17,"area":null},{"id":"2502.15208","title":"Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing","created":"2025-02-21","cited_by_count":15,"area":null},{"id":"2109.00363","title":"ConRPG: Paraphrase Generation using Contexts as Regularizer","created":"2021-09-01","cited_by_count":13,"area":null},{"id":"2204.01227","title":"Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors","created":"2022-04-04","cited_by_count":13,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"1908.10835","title":"An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation","created":"2019-08-28","cited_by_count":11,"area":"offlinerl"},{"id":"2204.08123","title":"Non-Parallel Text Style Transfer with Self-Parallel Supervision","created":"2022-04-18","cited_by_count":11,"area":null},{"id":"2103.12777","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","created":"2021-03-23","cited_by_count":10,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2403.16038","title":"Monotonic Paraphrasing Improves Generalization of Language Model Prompting","created":"2024-03-24","cited_by_count":10,"area":null},{"id":"2204.07696","title":"Efficient Reinforcement Learning for Unsupervised Controlled Text Generation","created":"2022-04-16","cited_by_count":7,"area":null},{"id":"2404.00303","title":"A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs","created":"2024-03-30","cited_by_count":7,"area":null},{"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,"area":"alignment"},{"id":"2106.00145","title":"Corpus-Based Paraphrase Detection Experiments and Review","created":"2021-05-31","cited_by_count":5,"area":null},{"id":"2110.01384","title":"Simulated annealing for optimization of graphs and sequences","created":"2021-10-01","cited_by_count":5,"area":null},{"id":"2210.13749","title":"AugCSE: Contrastive Sentence Embedding with Diverse Augmentations","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2106.05141","title":"AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2501.18649","title":"Fake News Detection After LLM Laundering: Measurement and Explanation","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2109.12457","title":"Learning to Selectively Learn for Weakly-supervised Paraphrase Generation","created":"2021-09-25","cited_by_count":3,"area":null},{"id":"2203.10483","title":"Entailment Relation Aware Paraphrase Generation","created":"2022-03-20","cited_by_count":3,"area":null},{"id":"2010.11553","title":"Incorporating Stylistic Lexical Preferences in Generative Language Models","created":"2020-10-22","cited_by_count":2,"area":"alignment"},{"id":"2110.00842","title":"Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning","created":"2021-10-02","cited_by_count":2,"area":null},{"id":"2301.07919","title":"Semantic-aware Contrastive Learning for More Accurate Semantic Parsing","created":"2023-01-19","cited_by_count":2,"area":null},{"id":"2302.01806","title":"Mitigating Data Scarcity for Large Language Models","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2306.05556","title":"Emotion and Sentiment Guided Paraphrasing","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2403.02271","title":"RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2412.17111","title":"Learning to Adapt to Low-Resource Paraphrase Generation","created":"2024-12-22","cited_by_count":2,"area":null},{"id":"2209.01765","title":"Continuous Decomposition of Granularity for Neural Paraphrase Generation","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2304.12519","title":"GlyphDiffusion: Text Generation as Image Generation","created":"2023-04-25","cited_by_count":1,"area":"diffusion"},{"id":"2403.17564","title":"Task-Oriented Paraphrase Analytics","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2109.02950","title":"Paraphrase Generation as Unsupervised Machine Translation","created":"2021-09-07","cited_by_count":0,"area":null},{"id":"2203.12106","title":"An Empirical Study on Learning and Improving the Search Objective for Unsupervised Paraphrasing","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2211.06014","title":"Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2305.13637","title":"IdEALS: Idiomatic Expressions for Advancement of Language Skills","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2310.04483","title":"Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2401.17827","title":"Neural Machine Translation for Malayalam Paraphrase Generation","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2405.11277","title":"Action Controlled Paraphrasing","created":"2024-05-18","cited_by_count":0,"area":null},{"id":"2506.02018","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","created":"2025-05-28","cited_by_count":0,"area":"alignment"},{"id":"2507.03415","title":"SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2509.15027","title":"CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.06383","title":"Protecting De-identified Documents from Search-based Linkage Attacks","created":"2025-10-07","cited_by_count":0,"area":null}],"next_cursor":null}