LangVAE and LangSpace: Building and Probing for Language Model VAEs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909597968629760 |
|---|---|
| author | Carvalho, Danilo S. Zhang, Yingji Unsworth, Harriet Freitas, André |
| author_facet | Carvalho, Danilo S. Zhang, Yingji Unsworth, Harriet Freitas, André |
| contents | We present LangVAE, a novel framework for modular construction of variational autoencoders (VAEs) on top of pre-trained large language models (LLMs). Such language model VAEs can encode the knowledge of their pre-trained components into more compact and semantically disentangled representations. The representations obtained in this way can be analysed with the LangVAE companion framework: LangSpace, which implements a collection of probing methods, such as vector traversal and interpolation, disentanglement measures, and cluster visualisations. LangVAE and LangSpace offer a flexible, efficient and scalable way of building and analysing textual representations, with simple integration for models available on the HuggingFace Hub. Additionally, we conducted a set of experiments with different encoder and decoder combinations, as well as annotated inputs, revealing a wide range of interactions across architectural families and sizes w.r.t. generalisation and disentanglement. Our findings demonstrate a promising framework for systematising the experimentation and understanding of textual representations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00004 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LangVAE and LangSpace: Building and Probing for Language Model VAEs Carvalho, Danilo S. Zhang, Yingji Unsworth, Harriet Freitas, André Computation and Language Artificial Intelligence We present LangVAE, a novel framework for modular construction of variational autoencoders (VAEs) on top of pre-trained large language models (LLMs). Such language model VAEs can encode the knowledge of their pre-trained components into more compact and semantically disentangled representations. The representations obtained in this way can be analysed with the LangVAE companion framework: LangSpace, which implements a collection of probing methods, such as vector traversal and interpolation, disentanglement measures, and cluster visualisations. LangVAE and LangSpace offer a flexible, efficient and scalable way of building and analysing textual representations, with simple integration for models available on the HuggingFace Hub. Additionally, we conducted a set of experiments with different encoder and decoder combinations, as well as annotated inputs, revealing a wide range of interactions across architectural families and sizes w.r.t. generalisation and disentanglement. Our findings demonstrate a promising framework for systematising the experimentation and understanding of textual representations. |
| title | LangVAE and LangSpace: Building and Probing for Language Model VAEs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2505.00004 |