arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.00699cs.CL
收藏

大型语言模型中污染检测方法的全面综述

A Comprehensive Survey of Contamination Detection Methods in Large Language Models

Nanyang Technological University(南洋理工大学);Institute of Infocomm Research (I2R), A*STAR(信息通信研究所(I2R),A*STAR);Salesforce Research(Salesforce研究)

Mathieu Ravaut, Bosheng Ding, Fangkai Jiao, Hailin Chen, Xingxuan Li, Ruochen Zhao, Chengwei Qin, Caiming Xiong, Shafiq Joty

AI总结:

本文综述了大型语言模型(LLMs)中污染检测的最新方法,分析了各类检测技术的原理与用例,并呼吁NLP研究界在模型评估中系统考虑污染偏差以保障评估可靠性。

摘要:

随着近年来大型语言模型(LLMs)的兴起,大量新机遇不断涌现,但也带来了新的挑战,其中污染正迅速成为关键问题。人工智能(AI)领域的商业应用和融资金额已达到一定规模,在流行的问答基准上获得的几个百分点的提升可能转化为数千万美元的收益,这给模型完整性带来了巨大压力。与此同时,追踪 LLMs 已经看过的数据变得越来越困难;对于像 GPT-4 和 Claude-3 这样不透露任何训练集信息的闭源模型来说,甚至是不可能的。因此,污染成为一个主要问题:LLMs 的性能可能不再可靠,因为其高性能可能至少部分归因于它们之前接触过这些数据。这一限制危及了自然语言处理(NLP)领域真实能力的提升,然而,目前仍缺乏如何高效检测污染的方法。在本文中,我们调查了近期所有关于 LLMs 污染检测的工作,分析了它们的方法论和用例,以阐明污染检测方法的正确使用。我们的工作呼吁 NLP 研究社区在 LLM 评估中系统地考虑污染偏差。

英文摘要:

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial Intelligence (AI) have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars, placing high pressure on model integrity. At the same time, it is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GPT-4 and Claude-3 not divulging any information on the training set. As a result, contamination becomes a major issue: LLMs' performance may not be reliable anymore, as the high performance may be at least partly due to their previous exposure to the data. This limitation jeopardizes real capability improvement in the field of NLP, yet, there remains a lack of methods on how to efficiently detect contamination. In this paper, we survey all recent work on contamination detection with LLMs, analyzing their methodologies and use cases to shed light on the appropriate usage of contamination detection methods. Our work calls the NLP research community's attention into systematically taking into account contamination bias in LLM evaluation.

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。

↑