arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.19840cs.CLcs.AI
收藏

AnomaLLMy——通过低置信度单token预测检测黑盒大语言模型中的异常token

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

Myre Laboratories(迈尔实验室)

Waligóra Witold

AI总结:

本文提出AnomaLLMy方法,通过低置信度单token预测以极低成本自动检测黑盒大语言模型中的异常token,并在GPT-4的token集上验证了其有效性。

摘要:

本文介绍了AnomaLLMy,一种用于自动检测仅提供API访问的黑盒大语言模型(LLMs)中异常token的新技术。AnomaLLMy利用低置信度单token预测作为一种经济高效的指标,识别模型行为中的不规则性,从而解决异常token降低模型质量和可靠性的问题。在GPT-4的token集cl100k_base数据集上验证时,AnomaLLMy检测到413个主要异常和65个次要异常,仅花费24.39美元的API额度,证明了该方法的高效性。本研究的见解有望对增强LLMs的鲁棒性和准确性有所裨益,特别是在tokenizer的开发与评估方面。

英文摘要:

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 cl100k_base 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑