arXiv Statistics ML
Token-Level Likelihood-Array Regression for Membership Inference and AI-Generated Text Detection
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Machine Learning
3d ago
Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees
The paper investigates why token prediction, a common pre‑training objective for language models, yields useful representations. It introduces a statistical framework linking token prediction accuracy to the geometry of token embeddings, showing that accurate predictions organize embeddings according to Hellinger distances between context distributions. The authors also propose a self‑consistency principle that refines contextual representations through repeated application of a shared block, and provide downstream guarantees for token generation, community recovery, and linear classification.
arXiv AI
Jul 24
Detecting LLM-Generated Tokens in Human--LLM Coauthored Text
arXiv:2607. 21458v1 Announce Type: new Abstract: The rise of human-AI collaborative writing has created a growing need for fine-grained detection methods that support localizing likely LLM-generated content in mixed-authorship documents.
arXiv Machine Learning
3d ago
Context Staircase: Signature-Aligned Dynamics of Token Embeddings under Small Initialization
arXiv:2608.30315v1 Announce Type: new Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lang...
arXiv AI
Jun 4
A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models
arXiv:2606. 04177v1 Announce Type: cross Abstract: Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users.
Hugging Face Trending Papers
Aug 11
Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection
Large language models (LLMs) are trained on massive and largely undisclosed corpora that may contain copyrighted or privacy-sensitive content. Data contamination detection (DCD) therefore aims to determine whether a given text is a member of the pre-training corpus of a target LLM.
Hugging Face Trending Papers
Jul 23
Detecting LLM-Generated Tokens in Human--LLM Coauthored Text
The rise of human-AI collaborative writing has created a growing need for fine-grained detection methods that support localizing likely LLM-generated content in mixed-authorship documents. Existing methods for detecting LLM-generated text mainly focus on document-level classification and cannot identify which parts of the text are generated by LLMs.