Research
The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models
arXiv:2606.13993v2 Announce Type: replace Abstract: A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learn
arXiv:2606.13993v2 Announce Type: replace 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.
Related
- Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster
- Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
- Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models
Source: arXiv cs.CL | 2026-08-04