Seonglae ChoOne Token Is Enough: Fingerprinting and Verifying Large Language...
Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm...
https://arxiv.org/abs/2607.10252
Measuring Behavioural Signatures of Large Language Models through...
Large language models (LLMs) increasingly mediate human decisions and communication, yet their behavioural regularities remain difficult to characterize systematically. We develop a...
https://arxiv.org/abs/2609.22934