小模型也能像人一样追踪故事里的角色变化，甚至超过人类。
Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives
- 用真实叙事测试模型和人类的实体追踪能力
- 4.1亿参数模型已达到人类水平，当前模型超越人类
- 适合对语言理解机制感兴趣的 researchers
理解语言需要在语篇中追踪实体——即知晓事物的位置及其变化，即使未明确说明。现有评估依赖人工任务，远离自然语言理解，且缺乏与人类的对比。本文通过多复杂度的真实叙事，同时评估语言模型与人类（N=48）的实体追踪表现。结果显示，人类的追踪能力随叙事复杂度下降，而非长度。语言模型在4.1亿参数时已达人类水平，随规模增长持续提升，当前模型远超人类表现。结果表明，作为语言理解核心的实体追踪，在远低于此前认为的模型规模下即可出现。
原文摘要 · Abstract (English)
Understanding language requires tracking entities across discourse - i.e., knowing where things are and how they change, even when not explicitly stated. Whether language models perform such tracking in a human-like fashion remains unclear, in part because existing evaluations rely on artificial tasks, far removed from natural language comprehension, and lack comparisons to humans. Here, we evaluate entity tracking in both language models and humans (N = 48) using naturalistic narratives at multiple levels of complexity. In humans, we find that entity tracking degrades specifically with narrative complexity, not narrative length. In language models, we find that human-level entity tracking is already present at 410 million parameters - well below the multi-billion parameter, code-specialised models identified by prior work - and improves with scale, with contemporary models far exceeding human performance. Together, these results demonstrate that entity tracking, a core component of language understanding, emerges at model scales far smaller than previously thought.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。