arXiv cs.CL· Alexander Spangher, Daniel E. Ho, Diyi Yang, Noah Goodman, Sanmi Koyejo·· 3 天前AI 评分31
语言模型的表达能力上限：LLM 概念传递的可表达性研究
Articulation Upper Bounds for Language Models
AI 导读
研究通过测量概念在两个 LLM 之间传递的效果，发现概念可分为三类：可完全表达（如"笑话以反转结尾"）、未来更强模型或可表达（如"故事世界观连贯性"）、以及面临可表达性上限（如"喜剧声音"，其含义与身份和社会群体意识绑定）。研究提出提示词优化算法，在基准上比现有算法提升最高 14%，并发现可恢复概念可通过定义和解释传递，不可恢复概念即使给出示例也无法传递。
正文 · 原文
Abstract:Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of language? We take steps towards measuring this in LLMs as follows: for a set of concepts, we measure how well each concept can be transmitted between two LLMs as their capabilities scale. This requires novel measurement tools: (1) optimal messages: we introduce a prompt optimization algorithm that beats existing algorithms by up to 14% on benchmarks and accurately estimates prompt upper bounds. (2) A transmission measure: the sender is asked to label text; the receiver then tries to recover the sender's prompt, and recovery is measured; we find this correlates strongly with human label error. With these measures, we use observational scaling laws to study how transmissibility of a concept, conveyed with optimal messages, increases as transmitter and receiver capacity grows: does it asymptote below or above a threshold? Measuring 1.2k concepts in eight domains, we find concepts that (a) can be fully articulated; these concepts usually depend on local patterns, e.g. "joke ends with surprise"; (b) might be articulated by future, stronger models; these rely on whole-text structural patterns, e.g. "story's worldbuilding coherence"; (c) concepts that face articulability limits; these concepts' meaning, we find, is tied to identity and social-group awareness, e.g. "comic voice". Interesting, these same concepts are not all challenging for humans: humans have moderate-to-high levels of agreement in 76% of concepts that LLMs struggle with; articulation limits, we find, are executor relative. Finally, we characterize the nature of improvement in each case: while recoverable concepts can be articulated through definitions and explanations, irrecoverable concepts cannot be transmitted, even with examples, and might require novel learning mechanisms.
| Comments: | 70 pages, preprint |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.19721 [cs.AI] |
| (or arXiv:2610.19721v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19721 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alexander Spangher [view email]
[v1]
Wed, 14 Oct 2026 07:47:31 UTC (283 KB)
来源：arXiv cs.CL · arxiv.org