Cover Image

Differentially-private text generation degrades output language quality

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Çano, Erion, Habernal, Ivan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How reparametrization trick broke differentially-private text representation learning
by: Habernal, Ivan
Published: (2022)

AlbNews: A Corpus of Headlines for Topic Modeling in Albanian
by: Çano, Erion, et al.
Published: (2024)

A Comprehensive Survey on Legal Summarization: Challenges and Future Directions
by: Akter, Mousumi, et al.
Published: (2025)

The Impact of Inference Acceleration on Bias of LLMs
by: Kirsten, Elisabeth, et al.
Published: (2024)

Large language models struggle with ethnographic text annotation
by: Goodall, Leonardo S., et al.
Published: (2026)

Beyond speculation: Measuring the growing presence of LLM-generated texts in multilingual disinformation
by: Macko, Dominik, et al.
Published: (2025)

Private Language Models via Truncated Laplacian Mechanism
by: Huang, Tianhao, et al.
Published: (2024)

Benchmark of stylistic variation in LLM-generated texts
by: Milička, Jiří, et al.
Published: (2025)

Are generative AI text annotations systematically biased?
by: Stolwijk, Sjoerd B., et al.
Published: (2025)

Can professional translators identify machine-generated text?
by: Farrell, Michael
Published: (2026)

ARC-Encoder: learning compressed text representations for large language models
by: Pilchen, Hippolyte, et al.
Published: (2025)

A Survey on Large Language Models for Automated Planning
by: Aghzal, Mohamed, et al.
Published: (2025)

Can postgraduate translation students identify machine-generated text?
by: Farrell, Michael
Published: (2025)

Hallucination as output-boundary misclassification: a composite abstention architecture for language models
by: Hintsanen, Angelina
Published: (2026)

ReadCtrl: Personalizing text generation with readability-controlled instruction learning
by: Tran, Hieu, et al.
Published: (2024)

A thorough benchmark of automatic text classification: From traditional approaches to large language models
by: Cunha, Washington, et al.
Published: (2025)

Large language models can consistently generate high-quality content for election disinformation operations
by: Williams, Angus R., et al.
Published: (2024)

Why is constrained neural language generation particularly challenging?
by: Garbacea, Cristina, et al.
Published: (2022)

MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning
by: Tran, Hieu, et al.
Published: (2025)

Humans can learn to detect AI-generated texts, or at least learn when they can't
by: Milička, Jiří, et al.
Published: (2025)

From text to multimodal: a survey of adversarial example generation in question answering systems
by: Yigit, Gulsum, et al.
Published: (2023)

Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection
by: Miralles-González, Pablo, et al.
Published: (2025)

DP-BART for Privatized Text Rewriting under Local Differential Privacy
by: Igamberdiev, Timour, et al.
Published: (2023)

Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A
by: Leschanowsky, Anna, et al.
Published: (2025)

Can pre-trained language models generate titles for research papers?
by: Rehman, Tohida, et al.
Published: (2024)

Stylometry recognizes human and LLM-generated texts in short samples
by: Przystalski, Karol, et al.
Published: (2025)

Improving the quality of Persian clinical text with a novel spelling correction system
by: Dashti, Seyed Mohammad Sadegh, et al.
Published: (2024)

ks-lit-3m: A 3.1 million word kashmiri text dataset for large language model pretraining
by: Malik, Haq Nawaz
Published: (2026)

Lightweight reranking for language model generations
by: Jain, Siddhartha, et al.
Published: (2023)

To share or not to share: What risks would laypeople accept to give sensitive data to differentially-private NLP systems?
by: Weiss, Christopher, et al.
Published: (2023)

<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs
by: Pletenev, Sergey, et al.
Published: (2025)

People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
by: Russell, Jenna, et al.
Published: (2025)

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations
by: Zhou, Yinghan, et al.
Published: (2025)

LLM-as-a-qualitative-judge: automating error analysis in natural language generation
by: Chirkova, Nadezhda, et al.
Published: (2025)

A systematic framework for generating novel experimental hypotheses from language models
by: Misra, Kanishka, et al.
Published: (2024)

Differentiate ChatGPT-generated and Human-written Medical Texts
by: Liao, Wenxiong, et al.
Published: (2023)

Enhancing textual textbook question answering with large language models and retrieval augmented generation
by: Alawwad, Hessa Abdulrahman, et al.
Published: (2024)

The "LLM World of Words" English free association norms generated by large language models
by: Abramski, Katherine, et al.
Published: (2024)

Syllable-level lyrics generation from melody exploiting character-level language model
by: Zhang, Zhe, et al.
Published: (2023)

Reshaping MOFs text mining with a dynamic multi-agents framework of large language model
by: Lin, Zuhong, et al.
Published: (2025)