The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models
Quick Answer
This study investigates the holistic storage of verb+up phrases in text-based LLMs and ASR models, revealing that frequency and predictability influence distinct representations.
Quick Take
This study investigates the holistic storage of verb+up phrases in text-based LLMs and ASR models, revealing that frequency and predictability influence distinct representations. The findings support usage-based theories of language, indicating that both model types exhibit evidence of holistic storage.
Key Points
- Holistic storage of verb+up phrases is influenced by frequency and predictability.
- Text-based LLMs and ASR models show distinct internal representations.
- The study supports usage-based theories of language acquisition.
- Previous research focused more on abstract knowledge than multi-word units.
- Findings suggest a need for further exploration of holistic storage in language models.
Paper Resources
Article Excerpt
From source RSS / original summaryarXiv:2606. 13993v1 Announce Type: new Abstract: A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learned representations, but also generate novel ones by applying productive rules. While recent work has examined abstract knowledge in language models, holistic storage of multi-word units has received far less attention.
We probe internal representations in text-based LLMs and an ASR model, testing whether V+up phrasal verbs develop distinct representations as a function of frequency and predictability. All models show evidence of holistic storage driven by frequency and predictability, further supporting usage-based theories of language.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.