RLCracker is a reinforcement learning attack that erases LLM watermarks at 98.5% success rate with minimal data and generalizes across ten schemes and multiple model sizes.
Ghostbuster: Detecting text ghostwritten by large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
ExaGPT uses span-level similarity retrieval from human and LLM datastores to detect machine-generated text while supplying the matching spans as human-interpretable evidence, achieving up to 37-point accuracy gains over prior interpretable detectors at 1% FPR.
GigaCheck detects LLM-generated text at both document and span levels by combining fine-tuned language-model embeddings with a DETR-like architecture that treats generated intervals as detectable objects.
Shared task findings show near-perfect binary detection of AI-generated text but greater difficulty in attributing outputs to particular language models.
citing papers explorer
-
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
RLCracker is a reinforcement learning attack that erases LLM watermarks at 98.5% success rate with minimal data and generalizes across ten schemes and multiple model sizes.
-
ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
ExaGPT uses span-level similarity retrieval from human and LLM datastores to detect machine-generated text while supplying the matching spans as human-interpretable evidence, achieving up to 37-point accuracy gains over prior interpretable detectors at 1% FPR.
-
GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization
GigaCheck detects LLM-generated text at both document and span levels by combining fine-tuned language-model embeddings with a DETR-like architecture that treats generated intervals as detectable objects.
-
Findings of the Counter Turing Test: AI-Generated Text Detection
Shared task findings show near-perfect binary detection of AI-generated text but greater difficulty in attributing outputs to particular language models.