Copertina

Effective Unsupervised Constrained Text Generation based on Perturbed Masking

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fu, Yingwen, Ou, Wenjie, Yu, Zhou, Lin, Yue
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions
di: Pan, Lei, et al.
Pubblicazione: (2024)

Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space
di: Yu, Xiaoyan, et al.
Pubblicazione: (2024)

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
di: Fu, Yu, et al.
Pubblicazione: (2023)

Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling
di: Kesgin, Himmet Toprak, et al.
Pubblicazione: (2024)

Adversarial Text Generation with Dynamic Contextual Perturbation
di: Waghela, Hetvi, et al.
Pubblicazione: (2025)

RepEval: Effective Text Evaluation with LLM Representation
di: Sheng, Shuqian, et al.
Pubblicazione: (2024)

Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis
di: Lee, Jun-Min, et al.
Pubblicazione: (2023)

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
di: Huang, Guanhua, et al.
Pubblicazione: (2024)

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
di: Yu, Longxuan, et al.
Pubblicazione: (2026)

Exploration of Masked and Causal Language Modelling for Text Generation
di: Micheletti, Nicolo, et al.
Pubblicazione: (2024)

Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking
di: Zhou, Mo, et al.
Pubblicazione: (2026)

PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
di: Chew, Oscar, et al.
Pubblicazione: (2025)

$\textit{LinkPrompt}$: Natural and Universal Adversarial Attacks on Prompt-based Language Models
di: Xu, Yue, et al.
Pubblicazione: (2024)

AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation
di: Iso, Hayate
Pubblicazione: (2022)

Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models
di: Chen, Xiang, et al.
Pubblicazione: (2023)

EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models
di: Rashid, Muhammad Shihab, et al.
Pubblicazione: (2024)

Unsupervised Text Style Transfer for Controllable Intensity
di: Gu, Shuhuan, et al.
Pubblicazione: (2026)

SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation
di: Fucci, Dennis, et al.
Pubblicazione: (2024)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
di: Shu, Huizhen, et al.
Pubblicazione: (2025)

Personalized Text Generation with Contrastive Activation Steering
di: Zhang, Jinghao, et al.
Pubblicazione: (2025)

On the (In)Effectiveness of Large Language Models for Chinese Text Correction
di: Li, Yinghui, et al.
Pubblicazione: (2023)

Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
di: Tu, Lifu, et al.
Pubblicazione: (2023)

RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts
di: Yang, Jing, et al.
Pubblicazione: (2024)

Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs
di: Hejabi, Parsa, et al.
Pubblicazione: (2025)

Scaling up Masked Diffusion Models on Text
di: Nie, Shen, et al.
Pubblicazione: (2024)

HiFlow: Hierarchical Feedback-Driven Optimization for Constrained Long-Form Text Generation
di: Zhu, Yifan, et al.
Pubblicazione: (2026)

Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models
di: Sun, Zhengke, et al.
Pubblicazione: (2025)

Modeling Low-Resource Health Coaching Dialogues via Neuro-Symbolic Goal Summarization and Text-Units-Text Generation
di: Zhou, Yue, et al.
Pubblicazione: (2024)

Chinese ModernBERT with Whole-Word Masking
di: Zhao, Zeyu, et al.
Pubblicazione: (2025)

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery
di: Sun, Yifan, et al.
Pubblicazione: (2025)

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
di: Yu, Longxuan, et al.
Pubblicazione: (2026)

Language Model as an Annotator: Unsupervised Context-aware Quality Phrase Generation
di: Zhang, Zhihao, et al.
Pubblicazione: (2023)

DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation
di: Chandradevan, Ramraj, et al.
Pubblicazione: (2024)

Language Models can Self-Lengthen to Generate Long Texts
di: Quan, Shanghaoran, et al.
Pubblicazione: (2024)

Towards Controlled Table-to-Text Generation with Scientific Reasoning
di: Guo, Zhixin, et al.
Pubblicazione: (2023)

AI-Generated Text is Non-Stationary: Detection via Temporal Tomography
di: West, Alva, et al.
Pubblicazione: (2025)

A Cognitive Writing Perspective for Constrained Long-Form Text Generation
di: Wan, Kaiyang, et al.
Pubblicazione: (2025)

Towards Cost-Effective Reward Guided Text Generation
di: Rashid, Ahmad, et al.
Pubblicazione: (2025)

Constrain Alignment with Sparse Autoencoders
di: Yin, Qingyu, et al.
Pubblicazione: (2024)

Contextual Text Denoising with Masked Language Models
di: Sun, Yifu, et al.
Pubblicazione: (2019)