Cover Image

Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cai, Shizhan, Ding, Liang, Tao, Dacheng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs
by: Wu, Yuchen, et al.
Published: (2025)

Intention Analysis Makes LLMs A Good Jailbreak Defender
by: Zhang, Yuqi, et al.
Published: (2024)

Healthcare Copilot: Eliciting the Power of General LLMs for Medical Consultation
by: Ren, Zhiyao, et al.
Published: (2024)

Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs
by: Lau, Gregory Kang Ruey, et al.
Published: (2024)

Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
by: Wu, Yuchen, et al.
Published: (2025)

KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance
by: Zhong, Qihuang, et al.
Published: (2025)

An Entropy-based Text Watermarking Detection Method
by: Lu, Yijian, et al.
Published: (2024)

SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
by: Hou, Abe Bohan, et al.
Published: (2023)

Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
by: Cai, Qifeng, et al.
Published: (2025)

E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
by: Zhong, Qihuang, et al.
Published: (2022)

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL
by: Zhong, Qihuang, et al.
Published: (2024)

Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
by: Wu, Yuchen, et al.
Published: (2025)

Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning
by: Zan, Changtong, et al.
Published: (2024)

Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation
by: Cai, Xiaodong, et al.
Published: (2025)

eTracer: Towards Traceable Text Generation via Claim-Level Grounding
by: Chu, Bohao, et al.
Published: (2026)

Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
by: Chen, Kunfeng, et al.
Published: (2026)

The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check
by: Lu, Qingyu, et al.
Published: (2026)

Self-Powered LLM Modality Expansion for Large Speech-Text Models
by: Yu, Tengfei, et al.
Published: (2024)

Watermark under Fire: A Robustness Evaluation of LLM Watermarking
by: Liang, Jiacheng, et al.
Published: (2024)

Revisiting Catastrophic Forgetting in Large Language Model Tuning
by: Li, Hongyu, et al.
Published: (2024)

Adaptive Testing for Segmenting Watermarked Texts From Language Models
by: Li, Xingchi, et al.
Published: (2025)

DebugLM: Learning Traceable Training Data Provenance for LLMs
by: Mo, Wenjie Jacky, et al.
Published: (2026)

Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
by: Han, Xia, et al.
Published: (2025)

REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models
by: Zhang, Ruisi, et al.
Published: (2023)

Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
by: Peng, Keqin, et al.
Published: (2025)

MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators
by: Lu, Qingyu, et al.
Published: (2024)

ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
by: Zhong, Qihuang, et al.
Published: (2024)

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
by: Zhong, Qihuang, et al.
Published: (2022)

TimeMark: A Trustworthy Time Watermarking Framework for Exact Generation-Time Recovery from AIGC
by: Che, Shangkun, et al.
Published: (2026)

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
by: Xiao, Yisong, et al.
Published: (2025)

Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation
by: Ren, Zhiyao, et al.
Published: (2026)

Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
by: Hoang, Duy C., et al.
Published: (2024)

Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning
by: Zhong, Qihuang, et al.
Published: (2025)

LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation
by: Wang, Keheng, et al.
Published: (2024)

On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs
by: Ding, Hanxing, et al.
Published: (2025)

Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
by: Gu, Tianle, et al.
Published: (2025)

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

BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation
by: Tariqul, Amit Bin, et al.
Published: (2026)

Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding
by: Peng, Keqin, et al.
Published: (2025)

Uncertainty Aware Learning for Language Model Alignment
by: Wang, Yikun, et al.
Published: (2024)