{"url":"/task/paraphrase-generation","name":"Paraphrase Generation","slug":"paraphrase-generation","description_markdown":"Paraphrase Generation involves transforming a natural language sentence to a new sentence, that has the same semantic meaning but a different syntactic or lexical surface form.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":209,"papers_with_code":74,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/paraphrase-generation-on-paralex","slug":"paraphrase-generation-on-paralex","dataset":"Paralex","dataset_url":"/dataset/paralex","rows_in_archive":2,"metrics":["iBLEU","BLEU"],"first_row_in_archive_order":{"model":"HRQ-VAE","paper_title":"Hierarchical Sketch Induction for Paraphrase Generation","paper_url":"/paper/hierarchical-sketch-induction-for-paraphrase","paper_date":"2022-03-07","arxiv_id":"2203.03463","code_links":[{"title":"tomhosking/hrq-vae","url":"https://github.com/tomhosking/hrq-vae"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/paraphrase-generation-on-quora-question-pairs-1","slug":"paraphrase-generation-on-quora-question-pairs-1","dataset":"Quora Question Pairs","dataset_url":"/dataset/quora-question-pairs","rows_in_archive":2,"metrics":["iBLEU","BLEU"],"first_row_in_archive_order":{"model":"HRQ-VAE","paper_title":"Hierarchical Sketch Induction for Paraphrase Generation","paper_url":"/paper/hierarchical-sketch-induction-for-paraphrase","paper_date":"2022-03-07","arxiv_id":"2203.03463","code_links":[{"title":"tomhosking/hrq-vae","url":"https://github.com/tomhosking/hrq-vae"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/paraphrase-generation-on-mscoco","slug":"paraphrase-generation-on-mscoco","dataset":"MSCOCO","dataset_url":"/dataset/mscoco","rows_in_archive":1,"metrics":["BLEU","iBLEU"],"first_row_in_archive_order":{"model":"HRQ-VAE","paper_title":"Hierarchical Sketch Induction for Paraphrase Generation","paper_url":"/paper/hierarchical-sketch-induction-for-paraphrase","paper_date":"2022-03-07","arxiv_id":"2203.03463","code_links":[{"title":"tomhosking/hrq-vae","url":"https://github.com/tomhosking/hrq-vae"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/mscoco","name":"MSCOCO","full_name":"","num_papers_in_archive":90},{"url":"/dataset/quora-question-pairs","name":"Quora Question Pairs","full_name":"","num_papers_in_archive":55},{"url":"/dataset/paralex","name":"Paralex","full_name":"","num_papers_in_archive":20},{"url":"/dataset/parabank","name":"ParaBank","full_name":"","num_papers_in_archive":17},{"url":"/dataset/opusparcus","name":"Opusparcus","full_name":"","num_papers_in_archive":15},{"url":"/dataset/paranmt-50m","name":"PARANMT-50M","full_name":"","num_papers_in_archive":13},{"url":"/dataset/opus","name":"OPUS","full_name":"open parallel corpus","num_papers_in_archive":12},{"url":"/dataset/duolingo-staple-shared-task","name":"Duolingo STAPLE Shared Task","full_name":"","num_papers_in_archive":10},{"url":"/dataset/quda","name":"Quda","full_name":"","num_papers_in_archive":4},{"url":"/dataset/textbox-2-0","name":"TextBox 2.0","full_name":"","num_papers_in_archive":3},{"url":"/dataset/stylekqc","name":"StyleKQC","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ap","name":"AP","full_name":"Adversarial Paraphrase","num_papers_in_archive":1},{"url":"/dataset/autoregressive-paraphrase-dataset-apd","name":"Autoregressive Paraphrase Dataset (ARPD)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/message-content-rephrasing","name":"Message Content Rephrasing","full_name":"","num_papers_in_archive":1},{"url":"/dataset/visp","name":"ViSP","full_name":"Vietnamese Sentence Paraphrases","num_papers_in_archive":1},{"url":"/dataset/chatgpt-paraphrases","name":"ChatGPT Paraphrases","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/multilingual-paraphrase-generation","name":"Multilingual Paraphrase Generation"}],"parent_tasks":[{"url":"/task/text-generation","name":"Text Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":74,"tagged_in_all":209,"items":[{"url":"/paper/paraphrase-types-for-generation-and-detection","title":"Paraphrase Types for Generation and Detection","date":"2023-10-23","arxiv_id":"2310.14863","repositories_listed":3,"syntology":null},{"url":"/paper/how-large-language-models-are-transforming","title":"How Large Language Models are Transforming Machine-Paraphrased Plagiarism","date":"2022-10-07","arxiv_id":"2210.03568","repositories_listed":3,"syntology":null},{"url":"/paper/chatgpt-to-replace-crowdsourcing-of","title":"ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness","date":"2023-05-22","arxiv_id":"2305.12947","repositories_listed":2,"syntology":null},{"url":"/paper/tess-text-to-text-self-conditioned-simplex","title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","date":"2023-05-15","arxiv_id":"2305.08379","repositories_listed":2,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/phrase-bert-improved-phrase-embeddings-from","title":"Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration","date":"2021-09-13","arxiv_id":"2109.06304","repositories_listed":2,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":2}},{"url":"/paper/reformulating-unsupervised-style-transfer-as","title":"Reformulating Unsupervised Style Transfer as Paraphrase Generation","date":"2020-10-12","arxiv_id":"2010.05700","repositories_listed":2,"syntology":{"n":19,"n_ran":9,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/syntax-guided-controlled-generation-of","title":"Syntax-guided Controlled Generation of Paraphrases","date":"2020-05-18","arxiv_id":"2005.08417","repositories_listed":2,"syntology":null},{"url":"/paper/neural-syntactic-preordering-for-controlled","title":"Neural Syntactic Preordering for Controlled Paraphrase Generation","date":"2020-05-05","arxiv_id":"2005.02013","repositories_listed":2,"syntology":null},{"url":"/paper/paraphrase-generation-with-latent-bag-of-1","title":"Paraphrase Generation with Latent Bag of Words","date":"2020-01-07","arxiv_id":"2001.01941","repositories_listed":2,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/learning-semantic-sentence-embeddings-using-1","title":"Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator","date":"2018-06-03","arxiv_id":"1806.00807","repositories_listed":2,"syntology":{"n":17,"n_ran":4,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/enhancing-paraphrase-type-generation-the","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","date":"2025-05-28","arxiv_id":"2506.02018","repositories_listed":1,"syntology":null},{"url":"/paper/a-large-scale-benchmark-for-vietnamese","title":"A Large-Scale Benchmark for Vietnamese Sentence Paraphrases","date":"2025-02-11","arxiv_id":"2502.07188","repositories_listed":1,"syntology":null},{"url":"/paper/smab-mab-based-word-sensitivity-estimation","title":"SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation","date":"2025-02-10","arxiv_id":"2502.07101","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/latent-paraphrasing-perturbation-on-layers","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","date":"2024-11-01","arxiv_id":"2411.00686","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/retrieve-generate-evaluate-a-case-study-for","title":"Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models","date":"2024-07-23","arxiv_id":"2407.16565","repositories_listed":1,"syntology":null},{"url":"/paper/action-controlled-paraphrasing","title":"Action Controlled Paraphrasing","date":"2024-05-18","arxiv_id":"2405.11277","repositories_listed":1,"syntology":null},{"url":"/paper/enforcing-paraphrase-generation-via","title":"Improved Paraphrase Generation via Controllable Latent Diffusion","date":"2024-04-13","arxiv_id":"2404.08938","repositories_listed":1,"syntology":null},{"url":"/paper/slpl-shroom-at-semeval-2024-task-06-a","title":"SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination","date":"2024-04-07","arxiv_id":"2404.04845","repositories_listed":1,"syntology":null},{"url":"/paper/a-quality-based-syntactic-template-retriever","title":"A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation","date":"2023-10-20","arxiv_id":"2310.13262","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-lexical-simplification-via","title":"Multilingual Lexical Simplification via Paraphrase Generation","date":"2023-07-28","arxiv_id":"2307.15286","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-syntactic-guidance-for-neural-text","title":"Explicit Syntactic Guidance for Neural Text Generation","date":"2023-06-20","arxiv_id":"2306.11485","repositories_listed":1,"syntology":null},{"url":"/paper/pip-parse-instructed-prefix-for-syntactically","title":"PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation","date":"2023-05-26","arxiv_id":"2305.16701","repositories_listed":1,"syntology":null},{"url":"/paper/paraamr-a-large-scale-syntactically-diverse","title":"ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation","date":"2023-05-26","arxiv_id":"2305.16585","repositories_listed":1,"syntology":null},{"url":"/paper/coedit-text-editing-by-task-specific","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","date":"2023-05-17","arxiv_id":"2305.09857","repositories_listed":1,"syntology":null},{"url":"/paper/translationese-reduction-using-abstract","title":"Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation","date":"2023-04-23","arxiv_id":"2304.11501","repositories_listed":1,"syntology":null},{"url":"/paper/paraphrasing-evades-detectors-of-ai-generated-1","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","date":"2023-03-23","arxiv_id":"2303.13408","repositories_listed":1,"syntology":null},{"url":"/paper/knn-box-a-unified-framework-for-nearest","title":"kNN-BOX: A Unified Framework for Nearest Neighbor Generation","date":"2023-02-27","arxiv_id":"2302.13574","repositories_listed":1,"syntology":null},{"url":"/paper/syntactically-robust-training-on-partially","title":"Syntactically Robust Training on Partially-Observed Data for Open Information Extraction","date":"2023-01-17","arxiv_id":"2301.06841","repositories_listed":1,"syntology":null},{"url":"/paper/deep-latent-variable-models-for-semi","title":"Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation","date":"2023-01-05","arxiv_id":"2301.02275","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-decomposition-of-granularity-for","title":"Continuous Decomposition of Granularity for Neural Paraphrase Generation","date":"2022-09-05","arxiv_id":"2209.01765","repositories_listed":1,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}