# AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions

arXiv: https://arxiv.org/abs/2406.19840 · HTML: https://mlsanity.com/paper/2406.19840/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 6 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Built on by (most cited first, 1 of 1)

- [ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs](https://mlsanity.com/paper/2504.05605/) (2025)

## Abstract (arXiv)

This paper introduces AnomaLLMy, a novel technique for the automatic detection of anomalous tokens in black-box Large Language Models (LLMs) with API-only access. Utilizing low-confidence single-token predictions as a cost-effective indicator, AnomaLLMy identifies irregularities in model behavior, addressing the issue of anomalous tokens degrading the quality and reliability of models. Validated on the cl100kbase dataset, the token set of GPT-4, AnomaLLMy detected 413 major and 65 minor anomalies, demonstrating the method's efficiency with just 24.39 spent in API credits. The insights from this research are expected to be beneficial for enhancing the robustness of and accuracy of LLMs, particularly in the development and assessment of tokenizers.