发表机构
KAIST AI（韩国科学技术院人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究大型语言模型中结构的存储、选择和修正问题，提出提升表示假设，通过多种实验评估其提升和细化情况，发现数据受嵌套规则和异常支配时模型存在问题，强调需研究数据与规则结构关系。
AI 中文摘要
大型语言模型（LLMs）常通过将个体观察映射到更通用的规则样结构来回答查询。但这些结构如何存储、选择和修正尚不清楚。为研究此过程，我们提出提升表示假设：LLMs通过共享潜在结构而非孤立的实例级事实更新记忆。我们通过上下文学习、LoRA和完全微调的受控异常学习实验评估LLMs的提升和细化。发现当数据受嵌套规则和异常支配时，LLMs易出现细化失败，而提升常过早发生。这些结果凸显研究LLMs中数据与规则结构关系的必要性。
英文摘要
Large language models (LLMs) adapt rapidly through fine-tuning and in-context learning, yet it remains unclear which inputs they treat as the same case and why their predictions change together. We introduce the Lifted State Hypothesis. Under fixed model parameters, context scope, and target computation, samples indistinguishable in their observed computation-relevant behavior form a computation-relative type. We hypothesize that compatible episodes activate a reusable latent component---a lifted state---that supports the target computation. State reuse enables type-level generalization but creates a non-monotonic revision problem. When later evidence distinguishes a subtype, revising a state still shared with its parent may affect members whose predictions should remain unchanged. The model must separate the subtype through rerouting, a new state, or input-specific compensation. We formalize this relation between generalization and revision. We introduce the NMR-Type Dataset to evaluate LLMs. The dataset first supports a broad modulo rule. It then provides conflicting supervision for a withheld subtype while replaying earlier examples. Across full fine-tuning, LoRA, and in-context learning, models often generalize the broad rule to the subtype but fail to localize its later revision. These results provide behavioral evidence consistent with the hypothesis and motivate further study of lifted-state formation and revision.
Comments24 pages, 13 figures
