Token rankings from language models are unique and NP-hard to forge, providing the first polynomially unforgeable model signature.
Authorship attribution for neural text generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
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.
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
-
Token Rankings are Unforgeable Language Model Signatures
Token rankings from language models are unique and NP-hard to forge, providing the first polynomially unforgeable model signature.
-
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
-
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.
-
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.