Large Language Models (LLMs) have achieved widespread adoption, yet our understanding of their behavior remains limited, particularly in detecting data contamination and hallucinations. While recently proposed probing techniques provide insights through activation analysis, they require "white-box" access to model internals, often unavailable. Current "gray-box" approaches typically analyze only the probability of the actual tokens in the sequence with simple task-specific heuristics. Importantly, these methods overlook the rich information contained in the full token distribution at each processing step. To address these limitations, we propose that gray-box analysis should leverage the complete observable output of LLMs, consisting of both the previously used token probabilities as well as the complete token distribution sequences - a unified data type we term LOS (LLM Output Signature). To this end, we develop a transformer-based approach to process LOS that theoretically guarantees approximation of existing techniques while enabling more nuanced analysis. Our approach achieves superior performance on hallucination and data contamination detection in gray-box settings, significantly outperforming existing baselines. Furthermore, it demonstrates strong transfer capabilities across datasets and LLMs, suggesting that LOS captures fundamental patterns in LLM behavior. Our code is available at:this https URL.
View on arXiv@article{bar-shalom2025_2503.14043,
title={ Learning on LLM Output Signatures for gray-box LLM Behavior Analysis },
author={ Guy Bar-Shalom and Fabrizio Frasca and Derek Lim and Yoav Gelberg and Yftah Ziser and Ran El-Yaniv and Gal Chechik and Haggai Maron },
journal={arXiv preprint arXiv:2503.14043},
year={ 2025 }
}