{"total":57,"rows":[{"id":"2411.18479","title":"SoK: Watermarking for AI-Generated Content","created":"2024-11-27","cited_by_count":51,"area":"safety"},{"id":"2410.02890","title":"Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach","created":"2024-10-03","cited_by_count":22,"area":"safety"},{"id":"2510.01268","title":"AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2411.11203","title":"Debiasing Watermarks for Large Language Models via Maximal Coupling","created":"2024-11-17","cited_by_count":19,"area":"safety"},{"id":"2405.11109","title":"Watermarking Language Models for Many Adaptive Users","created":"2024-05-17","cited_by_count":18,"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":"2502.10673","title":"Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs","created":"2025-02-15","cited_by_count":12,"area":"rag"},{"id":"2502.18049","title":"Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework","created":"2025-02-25","cited_by_count":10,"area":"synth"},{"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":"2601.06586","title":"Detecting LLM-Generated Text with Performance Guarantees","created":"2026-01-10","cited_by_count":10,"area":null},{"id":"2505.08878","title":"Optimized Couplings for Watermarking Large Language Models","created":"2025-05-13","cited_by_count":9,"area":"safety"},{"id":"2410.20418","title":"Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models","created":"2024-10-27","cited_by_count":8,"area":"inference"},{"id":"2502.06659","title":"Who Taught You That? Tracing Teachers in Model Distillation","created":"2025-02-10","cited_by_count":8,"area":"distill"},{"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":"2605.10977","title":"PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks","created":"2026-05-09","cited_by_count":7,"area":"safety"},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2510.03944","title":"On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2511.02083","title":"Watermarking Discrete Diffusion Language Models","created":"2025-11-03","cited_by_count":5,"area":"diffusion"},{"id":"2602.06754","title":"A Unified Framework for LLM Watermarks","created":"2026-02-06","cited_by_count":5,"area":"safety"},{"id":"2410.20670","title":"Segmenting Watermarked Texts From Language Models","created":"2024-10-28","cited_by_count":4,"area":"safety"},{"id":"2411.12764","title":"SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text","created":"2024-11-17","cited_by_count":4,"area":null},{"id":"2501.02441","title":"A Statistical Hypothesis Testing Framework for Data Misappropriation Detection in Large Language Models","created":"2025-01-05","cited_by_count":2,"area":null},{"id":"2602.14286","title":"Online LLM watermark detection via e-processes","created":"2026-02-15","cited_by_count":2,"area":"safety"},{"id":"2603.30017","title":"Refined Detection for Gumbel Watermarking","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.04344","title":"Perturbation is All You Need for Extrapolating Language Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2505.01484","title":"LLM Watermarking Using Mixtures and Statistical-to-Computational Gaps","created":"2025-05-02","cited_by_count":1,"area":"safety"},{"id":"2505.12507","title":"Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.06409","title":"HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions","created":"2025-06-06","cited_by_count":1,"area":"safety"},{"id":"2511.21600","title":"Robust Spectral Watermark for Synthetic Tabular Data","created":"2025-11-26","cited_by_count":1,"area":"safety"},{"id":"2602.01428","title":"Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models","created":"2026-02-01","cited_by_count":1,"area":"inference"},{"id":"2607.00224","title":"Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.05694","title":"Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking","created":"2026-07-06","cited_by_count":1,"area":"safety"},{"id":"2607.13003","title":"Watermark Forensics for Generative Models: An Information-Theoretic Perspective","created":"2026-07-14","cited_by_count":1,"area":"safety"},{"id":"2608.20839","title":"SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields","created":"2026-08-21","cited_by_count":1,"area":"diffusion"},{"id":"2407.14206","title":"Watermark Smoothing Attacks against Language Models","created":"2024-07-19","cited_by_count":0,"area":"safety"},{"id":"2502.08332","title":"Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark","created":"2025-02-12","cited_by_count":0,"area":"safety"},{"id":"2509.06120","title":"If generative AI is the answer, what is the question?","created":"2025-09-07","cited_by_count":0,"area":null},{"id":"2511.06645","title":"Adaptive Testing for Segmenting Watermarked Texts From Language Models","created":"2025-11-10","cited_by_count":0,"area":"safety"},{"id":"2512.00734","title":"Infinitely divisible privacy and beyond I: resolution of the $s^2=2k$ conjecture","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2512.04044","title":"MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking","created":"2025-12-03","cited_by_count":0,"area":"safety"},{"id":"2603.00105","title":"LIDS: LLM Summary Inference Under the Layered Lens","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.03410","title":"On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation","created":"2026-03-03","cited_by_count":0,"area":"safety"},{"id":"2604.11491","title":"ADD for Multi-Bit Image Watermarking","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.12890","title":"Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts","created":"2026-05-13","cited_by_count":0,"area":"mechinterp"},{"id":"2606.18430","title":"Signature filtering: a lightweight enhancement for statistical watermark detection in large language models","created":"2026-06-16","cited_by_count":0,"area":"safety"},{"id":"2607.07527","title":"A Unified Detection Framework for AI-Related Content and Artifacts","created":"2026-07-08","cited_by_count":0,"area":"safety"},{"id":"2607.21458","title":"Detecting LLM-Generated Tokens in Human--LLM Coauthored Text","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.21958","title":"Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes","created":"2026-07-24","cited_by_count":0,"area":"safety"},{"id":"2608.03093","title":"DHMark: Public-Key Watermarking for LLM-Generated Text via Diffie-Hellman-Guided Rejection Sampling","created":"2026-08-04","cited_by_count":0,"area":"safety"},{"id":"2608.10096","title":"Deciding When to Switch: E-Processes for Adaptive Minimax Training for Generative Adversarial Nets","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.18102","title":"Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text","created":"2026-06-09","cited_by_count":0,"area":"safety"},{"id":"2608.29030","title":"Learning to Follow In-Context Watermark Instructions via Self-Distillation","created":"2026-08-29","cited_by_count":0,"area":"safety"},{"id":"2609.03844","title":"Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2609.21858","title":"Watermarkable Multi-Draft Speculative Sampling via Poisson Processes","created":"2026-09-18","cited_by_count":0,"area":"inference"},{"id":"2610.14378","title":"Tokenization-Invariant Watermarking: A Byte-Local Method for LLM Text","created":"2026-10-09","cited_by_count":0,"area":"safety"},{"id":"2610.17655","title":"textGrain watermarking is harder to detect: can sum-tests still do it optimally?","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}