Paraphrase Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

17 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 74 papers with code (209 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Paraphrase Types for Generation and Detection
  23 Oct 2023 3 repositories listed
  Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language.
• How Large Language Models are Transforming Machine-Paraphrased Plagiarism
  7 Oct 2022 3 repositories listed
  The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work.
• ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness
  22 May 2023 2 repositories listed
  The emergence of generative large language models (LLMs) raises the question: what will be its impact on crowdsourcing?
• TESS: Text-to-Text Self-Conditioned Simplex Diffusion
  15 May 2023 2 repositories listed Syntology ran 0 of 15 samples · 15 unverified
  Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains.
• Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration
  13 Sep 2021 2 repositories listed Syntology ran 2 of 9 samples · 7 unverified · 2 pointer-only (licence)
  Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness.
• Reformulating Unsupervised Style Transfer as Paraphrase Generation
  12 Oct 2020 2 repositories listed Syntology ran 9 of 19 samples · 10 unverified
  Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of…
• Syntax-guided Controlled Generation of Paraphrases
  18 May 2020 2 repositories listed
  In these methods, syntactic-guidance is sourced from a separate exemplar sentence.
• Neural Syntactic Preordering for Controlled Paraphrase Generation
  5 May 2020 2 repositories listed
  Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or…
• Paraphrase Generation with Latent Bag of Words
  7 Jan 2020 2 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  Inspired by variational autoencoders with discrete latent structures, in this work, we propose a latent bag of words (BOW) model for paraphrase generation.
• Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
  3 Jun 2018 2 repositories listed Syntology ran 4 of 17 samples · 13 unverified
  One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.
• Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data
  28 May 2025 1 repository listed
  The PTD model surpasses automated metrics and provides a more reliable framework for evaluating paraphrase quality, advancing paraphrase-type research toward richer, user-aligned language generation and establishing a…
• A Large-Scale Benchmark for Vietnamese Sentence Paraphrases
  11 Feb 2025 1 repository listed
  This paper presents ViSP, a high-quality Vietnamese dataset for sentence paraphrasing, consisting of 1.
• SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
  10 Feb 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  To understand the complexity of sequence classification tasks, Hahn et al.
• Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
  1 Nov 2024 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  As Large Language Models (LLMs) are increasingly deployed in specialized domains with continuously evolving knowledge, the need for timely and precise knowledge injection has become essential.
• Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models
  23 Jul 2024 1 repository listed
  Recent surge in the accessibility of large language models (LLMs) to the general population can lead to untrackable use of such models for medical-related recommendations.
• Action Controlled Paraphrasing
  18 May 2024 1 repository listed
  To address the inference gap, we introduce an optional action token as a placeholder that encourages the model to determine the appropriate action independently when users' intended actions are not provided.
• Improved Paraphrase Generation via Controllable Latent Diffusion
  13 Apr 2024 1 repository listed
  Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel.
• SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
  7 Apr 2024 1 repository listed
  Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text.
• A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
  20 Oct 2023 1 repository listed
  Furthermore, for situations requiring multiple paraphrases for each source sentence, we design a Diverse Templates Search (DTS) algorithm, which can enhance the diversity between paraphrases without sacrificing quality.
• Multilingual Lexical Simplification via Paraphrase Generation
  28 Jul 2023 1 repository listed
  After feeding the input sentence into the encoder of paraphrase modeling, we generate the substitutes based on a novel decoding strategy that concentrates solely on the lexical variations of the complex word.
• Explicit Syntactic Guidance for Neural Text Generation
  20 Jun 2023 1 repository listed
  Most existing text generation models follow the sequence-to-sequence paradigm.
• PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation
  26 May 2023 1 repository listed
  Existing fine-tuning methods for this task are costly as all the parameters of the model need to be updated during the training process.
• ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation
  26 May 2023 1 repository listed
  Paraphrase generation is a long-standing task in natural language processing (NLP).
• CoEdIT: Text Editing by Task-Specific Instruction Tuning
  17 May 2023 1 repository listed
  We present a large language model fine-tuned on a diverse collection of task-specific instructions for text editing (a total of 82K instructions).
• Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation
  23 Apr 2023 1 repository listed
  Though individual translated texts are often fluent and preserve meaning, at a large scale, translated texts have statistical tendencies which distinguish them from text originally written in the language…
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
  23 Mar 2023 1 repository listed
  To increase the robustness of AI-generated text detection to paraphrase attacks, we introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API…
• kNN-BOX: A Unified Framework for Nearest Neighbor Generation
  27 Feb 2023 1 repository listed
  Augmenting the base neural model with a token-level symbolic datastore is a novel generation paradigm and has achieved promising results in machine translation (MT).
• Syntactically Robust Training on Partially-Observed Data for Open Information Extraction
  17 Jan 2023 1 repository listed
  In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation.
• Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation
  5 Jan 2023 1 repository listed
  To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model.
• Continuous Decomposition of Granularity for Neural Paraphrase Generation
  5 Sep 2022 1 repository listed
  While Transformers have had significant success in paragraph generation, they treat sentences as linear sequences of tokens and often neglect their hierarchical information.

Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.