arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15028cs.LGcs.AI
收藏

长上下文,少关注:通过隐私和个性化揭示LLM中的缩放差距

Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization

University of California, Berkeley(加州大学伯克利分校)

Shangding Gu

AI总结:

本文通过PAPerBench基准测试揭示了LLM在长上下文情况下个性化和隐私保护性能下降的缩放差距,分析了注意力稀释的理论机制。

摘要:

大型语言模型(LLMs)越来越多地应用于隐私关键和个性化导向的场景,但上下文长度在塑造隐私泄露和个性化效果中的作用仍鲜有研究。我们引入了一个大规模基准测试集PAPerBench,系统研究增加上下文长度如何影响LLMs的个性化质量和隐私保护。该基准测试集包含约29,000个实例,上下文长度从1K到256K tokens不等,产生总计377K个评估问题。它在多样化的场景中联合评估个性化性能和隐私风险,使能够对长上下文模型行为进行受控分析。在最先进的LLMs上进行的广泛评估揭示了随着上下文长度增加,个性化和隐私性能均出现一致的退化。我们进一步提供了上下文缩放下注意力稀释的理论分析,解释这种行为是固定容量Transformer中软注意力的固有限制。经验与理论发现共同表明当前模型存在一个普遍的缩放差距——长上下文,少关注。我们发布该基准测试集以支持可重复的评估和未来关于可扩展隐私和个性化的研究。代码和数据可在https://github.com/SafeRL-Lab/PAPerBench获取。

英文摘要:

Large language models (LLMs) are increasingly deployed in privacy-critical and personalization-oriented scenarios, yet the role of context length in shaping privacy leakage and personalization effectiveness remains largely unexplored. We introduce a large-scale benchmark, PAPerBench, to systematically study how increasing context length influences both personalization quality and privacy protection in LLMs. The benchmark comprises approximately 29,000 instances with context lengths ranging from 1K to 256K tokens, yielding a total of 377K evaluation questions. It jointly evaluates personalization performance and privacy risks across diverse scenarios, enabling controlled analysis of long-context model behavior. Extensive evaluations across state-of-the-art LLMs reveal consistent performance degradation in both personalization and privacy as context length increases. We further provide a theoretical analysis of attention dilution under context scaling, explaining this behavior as an inherent limitation of soft attention in fixed-capacity Transformers. The empirical and theoretical findings together suggest a general scaling gap in current models -- long context, less focus. We release the benchmark to support reproducible evaluation and future research on scalable privacy and personalization. Code and data are available at https://github.com/SafeRL-Lab/PAPerBench

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。

↑