{"total":141,"rows":[{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2310.06356","title":"A Semantic Invariant Robust Watermark for Large Language Models","created":"2023-10-10","cited_by_count":112,"area":"safety"},{"id":"2312.07913","title":"A Survey of Text Watermarking in the Era of Large Language Models","created":"2023-12-13","cited_by_count":112,"area":"safety"},{"id":"2405.10051","title":"MarkLLM: An Open-Source Toolkit for LLM Watermarking","created":"2024-05-16","cited_by_count":95,"area":"safety"},{"id":"2403.13485","title":"An Entropy-based Text Watermarking Detection Method","created":"2024-03-20","cited_by_count":75,"area":"safety"},{"id":"2310.15654","title":"A Survey on Detection of LLMs-Generated Content","created":"2023-10-24","cited_by_count":71,"area":null},{"id":"2312.00273","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","created":"2023-12-01","cited_by_count":71,"area":"safety"},{"id":"2401.13927","title":"Adaptive Text Watermark for Large Language Models","created":"2024-01-25","cited_by_count":67,"area":"safety"},{"id":"2307.16230","title":"An Unforgeable Publicly Verifiable Watermark for Large Language Models","created":"2023-07-30","cited_by_count":65,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2308.00221","title":"Advancing Beyond Identification: Multi-bit Watermark for Large Language Models","created":"2023-08-01","cited_by_count":57,"area":"safety"},{"id":"2307.15992","title":"Towards Codable Watermarking for Injecting Multi-bits Information to LLMs","created":"2023-07-29","cited_by_count":54,"area":"safety"},{"id":"2411.18479","title":"SoK: Watermarking for AI-Generated Content","created":"2024-11-27","cited_by_count":51,"area":"safety"},{"id":"2307.13808","title":"Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy","created":"2023-07-25","cited_by_count":50,"area":"safety"},{"id":"2401.16820","title":"Provably Robust Multi-bit Watermarking for AI-generated Text","created":"2024-01-30","cited_by_count":47,"area":"safety"},{"id":"2402.02333","title":"Copyright Protection in Generative AI: A Technical Perspective","created":"2024-02-04","cited_by_count":38,"area":null},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2402.18059","title":"Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models","created":"2024-02-28","cited_by_count":34,"area":"safety"},{"id":"2401.06461","title":"Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers","created":"2024-01-12","cited_by_count":27,"area":null},{"id":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2312.17295","title":"Optimizing watermarks for large language models","created":"2023-12-28","cited_by_count":25,"area":"safety"},{"id":"2310.05103","title":"Zero-Shot Detection of Machine-Generated Codes","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2404.15639","title":"CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code","created":"2024-04-24","cited_by_count":24,"area":"safety"},{"id":"2505.11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","created":"2025-05-14","cited_by_count":24,"area":"safety"},{"id":"2409.00089","title":"Watermarking Techniques for Large Language Models: A Survey","created":"2024-08-26","cited_by_count":23,"area":"safety"},{"id":"2506.09046","title":"Self-Evolving Multi-Agent Systems via Textual Backpropagation","created":"2025-06-10","cited_by_count":23,"area":"agents"},{"id":"2403.10553","title":"Learning to Watermark LLM-generated Text via Reinforcement Learning","created":"2024-03-13","cited_by_count":22,"area":"safety"},{"id":"2508.11548","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","created":"2025-08-15","cited_by_count":20,"area":"safety"},{"id":"2502.11598","title":"Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?","created":"2025-02-17","cited_by_count":19,"area":"safety"},{"id":"2503.04636","title":"Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking","created":"2025-03-06","cited_by_count":19,"area":"safety"},{"id":"2410.02099","title":"A Watermark for Black-Box Language Models","created":"2024-10-02","cited_by_count":16,"area":"safety"},{"id":"2405.19677","title":"Large Language Model Watermark Stealing With Mixed Integer Programming","created":"2024-05-30","cited_by_count":14,"area":"safety"},{"id":"2410.06467","title":"WAPITI: A Watermark for Finetuned Open-Source LLMs","created":"2024-10-09","cited_by_count":12,"area":"safety"},{"id":"2507.14067","title":"VLA-Mark: A cross modal watermark for large vision-language alignment model","created":"2025-07-18","cited_by_count":12,"area":"mllm"},{"id":"2403.13000","title":"Duwak: Dual Watermarks in Large Language Models","created":"2024-03-12","cited_by_count":11,"area":"safety"},{"id":"2412.05139","title":"A Practical Examination of AI-Generated Text Detectors for Large Language Models","created":"2024-12-06","cited_by_count":11,"area":null},{"id":"2502.18851","title":"Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code","created":"2025-02-26","cited_by_count":10,"area":"safety"},{"id":"2504.06575","title":"Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning","created":"2025-04-09","cited_by_count":10,"area":"safety"},{"id":"2505.16934","title":"In-Context Watermarks for Large Language Models","created":"2025-05-22","cited_by_count":10,"area":"safety"},{"id":"2409.05112","title":"WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents","created":"2024-09-08","cited_by_count":9,"area":null},{"id":"2411.13425","title":"Watermark under Fire: A Robustness Evaluation of LLM Watermarking","created":"2024-11-20","cited_by_count":9,"area":"safety"},{"id":"2507.06274","title":"Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks","created":"2025-07-08","cited_by_count":9,"area":"safety"},{"id":"2312.12918","title":"Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors","created":"2023-12-20","cited_by_count":8,"area":null},{"id":"2404.02138","title":"Topic-Based Watermarks for Large Language Models","created":"2024-04-02","cited_by_count":8,"area":"safety"},{"id":"2505.16530","title":"DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection","created":"2025-05-22","cited_by_count":8,"area":"safety"},{"id":"2601.03294","title":"AgentMark: Utility-Preserving Behavioral Watermarking for Agents","created":"2026-01-05","cited_by_count":8,"area":"agents"},{"id":"2409.09739","title":"PersonaMark: Personalized LLM watermarking for model protection and user attribution","created":"2024-09-15","cited_by_count":7,"area":"safety"},{"id":"2508.08211","title":"SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders","created":"2025-08-11","cited_by_count":7,"area":"safety"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"area":"safety"},{"id":"2402.07518","title":"Efficient and Universal Watermarking for LLM-Generated Code Detection","created":"2024-02-12","cited_by_count":6,"area":"safety"},{"id":"2410.02693","title":"Discovering Spoofing Attempts on Language Model Watermarks","created":"2024-10-03","cited_by_count":6,"area":"safety"},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2505.14112","title":"Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2510.10987","title":"DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation","created":"2025-10-13","cited_by_count":6,"area":"safety"},{"id":"2511.07863","title":"WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking","created":"2025-11-11","cited_by_count":6,"area":"safety"},{"id":"2505.09924","title":"From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models","created":"2025-05-15","cited_by_count":5,"area":"safety"},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2509.07755","title":"Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts","created":"2025-09-09","cited_by_count":5,"area":"safety"},{"id":"2510.21053","title":"A Reinforcement Learning Framework for Robust and Secure LLM Watermarking","created":"2025-10-23","cited_by_count":5,"area":"safety"},{"id":"2605.12456","title":"TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection","created":"2026-05-12","cited_by_count":5,"area":"safety"},{"id":"2412.03107","title":"CredID: Credible Multi-Bit Watermark for Large Language Models Identification","created":"2024-12-04","cited_by_count":4,"area":"safety"},{"id":"2502.16699","title":"Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations","created":"2025-02-23","cited_by_count":4,"area":"safety"},{"id":"2502.17749","title":"Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2504.06446","title":"Can you Finetune your Binoculars? Embedding Text Watermarks into the Weights of Large Language Models","created":"2025-04-08","cited_by_count":4,"area":"safety"},{"id":"2505.02344","title":"An End-to-End Model for Logits-Based Large Language Models Watermarking","created":"2025-05-05","cited_by_count":4,"area":"safety"},{"id":"2508.03829","title":"Majority Bit-Aware Watermarking For Large Language Models","created":"2025-08-05","cited_by_count":4,"area":"safety"},{"id":"2602.18700","title":"Watermarking LLM Agent Trajectories","created":"2026-02-21","cited_by_count":4,"area":"agents"},{"id":"2312.06488","title":"Performance-lossless Black-box Model Watermarking","created":"2023-12-11","cited_by_count":3,"area":"safety"},{"id":"2402.16889","title":"Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation","created":"2024-02-23","cited_by_count":3,"area":"safety"},{"id":"2406.11106","title":"From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models","created":"2024-06-17","cited_by_count":3,"area":"safety"},{"id":"2501.02446","title":"RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework","created":"2025-01-05","cited_by_count":3,"area":"safety"},{"id":"2501.12174","title":"BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks","created":"2025-01-21","cited_by_count":3,"area":"safety"},{"id":"2504.03765","title":"Watermarking for AI Content Detection: A Review on Text, Visual, and Audio Modalities","created":"2025-04-02","cited_by_count":3,"area":"safety"},{"id":"2506.04462","title":"Watermarking Degrades Alignment in Language Models: Analysis and Mitigation","created":"2025-06-04","cited_by_count":3,"area":"alignment"},{"id":"2506.07403","title":"Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness","created":"2025-06-09","cited_by_count":3,"area":"safety"},{"id":"2510.02342","title":"CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models","created":"2025-09-27","cited_by_count":3,"area":"safety"},{"id":"2601.05144","title":"Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models","created":"2026-01-08","cited_by_count":3,"area":"lr"},{"id":"2601.07291","title":"A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model","created":"2026-01-12","cited_by_count":3,"area":"mllm"},{"id":"2603.17445","title":"When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditing","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2410.19096","title":"Watermarking Large Language Models and the Generated Content: Opportunities and Challenges","created":"2024-10-24","cited_by_count":2,"area":"safety"},{"id":"2506.05594","title":"SoK: Are Watermarks in LLMs Ready for Deployment?","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"id":"2506.06991","title":"Evaluating LLM-Contaminated Crowdsourcing Data Without Ground Truth","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2509.20924","title":"RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks","created":"2025-09-25","cited_by_count":2,"area":"safety"},{"id":"2510.09007","title":"LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data","created":"2025-10-10","cited_by_count":2,"area":"safety"},{"id":"2510.12828","title":"SimKey: A Semantically Aware Key Module for Watermarking Language Models","created":"2025-10-11","cited_by_count":2,"area":"safety"},{"id":"2510.13829","title":"A Linguistics-Aware LLM Watermarking via Syntactic Predictability","created":"2025-10-10","cited_by_count":2,"area":"safety"},{"id":"2510.26274","title":"PVMark: Enabling Public Verifiability for LLM Watermarking Schemes","created":"2025-10-30","cited_by_count":2,"area":"safety"},{"id":"2512.16904","title":"How Good is Post-Hoc Watermarking With Language Model Rephrasing?","created":"2025-12-18","cited_by_count":2,"area":"safety"},{"id":"2604.11546","title":"RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience","created":"2026-04-13","cited_by_count":2,"area":"safety"},{"id":"2604.22438","title":"SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking","created":"2026-04-24","cited_by_count":2,"area":"safety"},{"id":"2605.13095","title":"Watermarking Should Be Treated as a Monitoring Primitive","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2408.01354","title":"MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code","created":"2024-08-02","cited_by_count":1,"area":"safety"},{"id":"2410.04454","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2506.06069","title":"Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.13494","title":"Watermarking LLM-Generated Datasets in Downstream Tasks","created":"2025-06-16","cited_by_count":1,"area":"safety"},{"id":"2508.11925","title":"Optimizing Token Choice for Code Watermarking: An RL Approach","created":"2025-08-16","cited_by_count":1,"area":"safety"}],"next_cursor":"100"}