Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents
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_ | 1866911075258073088 |
|---|---|
| author | Yan, Xinyuan Sevastjanova, Rita van der Ben, Sinie El-Assady, Mennatallah Wang, Bei |
| author_facet | Yan, Xinyuan Sevastjanova, Rita van der Ben, Sinie El-Assady, Mennatallah Wang, Bei |
| contents | Large language models (LLMs) produce high-dimensional embeddings that capture rich semantic and syntactic relationships between words, sentences, and concepts. Investigating the topological structures of LLM embedding spaces via mapper graphs enables us to understand their underlying structures. Specifically, a mapper graph summarizes the topological structure of the embedding space, where each node represents a topological neighborhood (containing a cluster of embeddings), and an edge connects two nodes if their corresponding neighborhoods overlap. However, manually exploring these embedding spaces to uncover encoded linguistic properties requires considerable human effort. To address this challenge, we introduce a framework for semi-automatic annotation of these embedding properties. To organize the exploration process, we first define a taxonomy of explorable elements within a mapper graph such as nodes, edges, paths, components, and trajectories. The annotation of these elements is executed through two types of customizable LLM-based agents that employ perturbation techniques for scalable and automated analysis. These agents help to explore and explain the characteristics of mapper elements and verify the robustness of the generated explanations. We instantiate the framework within a visual analytics workspace and demonstrate its effectiveness through case studies. In particular, we replicate findings from prior research on BERT's embedding properties across various layers of its architecture and provide further observations into the linguistic properties of topological neighborhoods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_18607 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents Yan, Xinyuan Sevastjanova, Rita van der Ben, Sinie El-Assady, Mennatallah Wang, Bei Computational Geometry Machine Learning Large language models (LLMs) produce high-dimensional embeddings that capture rich semantic and syntactic relationships between words, sentences, and concepts. Investigating the topological structures of LLM embedding spaces via mapper graphs enables us to understand their underlying structures. Specifically, a mapper graph summarizes the topological structure of the embedding space, where each node represents a topological neighborhood (containing a cluster of embeddings), and an edge connects two nodes if their corresponding neighborhoods overlap. However, manually exploring these embedding spaces to uncover encoded linguistic properties requires considerable human effort. To address this challenge, we introduce a framework for semi-automatic annotation of these embedding properties. To organize the exploration process, we first define a taxonomy of explorable elements within a mapper graph such as nodes, edges, paths, components, and trajectories. The annotation of these elements is executed through two types of customizable LLM-based agents that employ perturbation techniques for scalable and automated analysis. These agents help to explore and explain the characteristics of mapper elements and verify the robustness of the generated explanations. We instantiate the framework within a visual analytics workspace and demonstrate its effectiveness through case studies. In particular, we replicate findings from prior research on BERT's embedding properties across various layers of its architecture and provide further observations into the linguistic properties of topological neighborhoods. |
| title | Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents |
| topic | Computational Geometry Machine Learning |
| url | https://arxiv.org/abs/2507.18607 |