语言模型中的进化与压缩:关于人类对齐分类的出现
Evolution and compression in LLMs: On the emergence of human-aligned categorization
AI总结:
研究探讨LLM是否能进化出高效的人类对齐语义系统,通过颜色分类实验发现,大模型在复杂性和英语对齐性上表现各异,仅最强模型能复现人类近最优的信息瓶颈贸易-offs。
摘要:
越来越多的证据表明,人类的语义类别系统通过信息瓶颈(IB)复杂度-准确性权衡实现近最优压缩。大型语言模型(LLM)并非为此目标训练,因此问题浮现:LLM能否进化出高效的人类对齐语义系统?为回答此问题,我们聚焦颜色分类——认知分类理论的关键测试场,且拥有独特丰富的人类数据——并用LLM复现两项重要的人类研究。首先,我们进行了英语颜色命名研究,显示LLM在复杂性和英语对齐性上差异显著,较大规模指令调优模型在对齐性和IB效率上表现更优。其次,为测试这些LLM是否仅模仿训练数据中的模式,或实际表现出人类般的归纳偏倚倾向IB效率,我们通过一种称为迭代上下文语言学习(IICLL)的方法在LLM中模拟伪颜色命名系统的文化进化。我们发现,类似人类,LLM会迭代重构最初随机的系统,朝着更高的IB效率发展。然而,只有具备最强上下文能力的模型(Gemini 2.0)才能复现人类观察到的广泛近最优IB权衡范围,而其他最先进的模型则收敛到低复杂度解决方案。这些发现展示了如何通过与人类语义效率相同的根本原则,在LLM中产生人类对齐的语义类别。
英文摘要:
Converging evidence suggests that human systems of semantic categories achieve near-optimal compression via the Information Bottleneck (IB) complexity-accuracy tradeoff. Large language models (LLMs) are not trained for this objective, which raises the question: are LLMs capable of evolving efficient human-aligned semantic systems? To address this question, we focus on color categorization -- a key testbed of cognitive theories of categorization with uniquely rich human data -- and replicate with LLMs two influential human studies. First, we conduct an English color-naming study, showing that LLMs vary widely in their complexity and English-alignment, with larger instruction-tuned models achieving better alignment and IB-efficiency. Second, to test whether these LLMs simply mimic patterns in their training data or actually exhibit a human-like inductive bias toward IB-efficiency, we simulate cultural evolution of pseudo color-naming systems in LLMs via a method we refer to as Iterated in-Context Language Learning (IICLL). We find that akin to humans, LLMs iteratively restructure initially random systems towards greater IB-efficiency. However, only a model with strongest in-context capabilities (Gemini 2.0) is able to recapitulate the wide range of near-optimal IB-tradeoffs observed in humans, while other state-of-the-art models converge to low-complexity solutions. These findings demonstrate how human-aligned semantic categories can emerge in LLMs via the same fundamental principle that underlies semantic efficiency in humans.
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。