Score: 1

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Published: March 5, 2025 | arXiv ID: 2503.03601v1

By: Kristian Kuznetsov , Laida Kushnareva , Polina Druzhinina and more

Potential Business Impact:

Finds fake writing from smart computer programs.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Artificial Text Detection (ATD) is becoming increasingly important with the rise of advanced Large Language Models (LLMs). Despite numerous efforts, no single algorithm performs consistently well across different types of unseen text or guarantees effective generalization to new LLMs. Interpretability plays a crucial role in achieving this goal. In this study, we enhance ATD interpretability by using Sparse Autoencoders (SAE) to extract features from Gemma-2-2b residual stream. We identify both interpretable and efficient features, analyzing their semantics and relevance through domain- and model-specific statistics, a steering approach, and manual or LLM-based interpretation. Our methods offer valuable insights into how texts from various models differ from human-written content. We show that modern LLMs have a distinct writing style, especially in information-dense domains, even though they can produce human-like outputs with personalized prompts.

Repos / Data Links

Page Count
22 pages

Category
Computer Science:
Computation and Language