LangLasso: Interactive Cluster Descriptions through LLM Explanation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911377628594176 |
|---|---|
| author | Buchmüller, Raphael Collaris, Dennis Meng, Linhao Chatzimparmpas, Angelos |
| author_facet | Buchmüller, Raphael Collaris, Dennis Meng, Linhao Chatzimparmpas, Angelos |
| contents | Dimensionality reduction is a powerful technique for revealing structure and potential clusters in data. However, as the axes are complex, non-linear combinations of features, they often lack semantic interpretability. Existing visual analytics (VA) methods support cluster interpretation through feature comparison and interactive exploration, but they require technical expertise and intense human effort. We present \textit{LangLasso}, a novel method that complements VA approaches through interactive, natural language descriptions of clusters using large language models (LLMs). It produces human-readable descriptions that make cluster interpretation accessible to non-experts and allow integration of external contextual knowledge beyond the dataset. We systematically evaluate the reliability of these explanations and demonstrate that \langlasso provides an effective first step for engaging broader audiences in cluster interpretation. The tool is available at https://langlasso.vercel.app |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10458 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LangLasso: Interactive Cluster Descriptions through LLM Explanation Buchmüller, Raphael Collaris, Dennis Meng, Linhao Chatzimparmpas, Angelos Human-Computer Interaction Machine Learning Computation Dimensionality reduction is a powerful technique for revealing structure and potential clusters in data. However, as the axes are complex, non-linear combinations of features, they often lack semantic interpretability. Existing visual analytics (VA) methods support cluster interpretation through feature comparison and interactive exploration, but they require technical expertise and intense human effort. We present \textit{LangLasso}, a novel method that complements VA approaches through interactive, natural language descriptions of clusters using large language models (LLMs). It produces human-readable descriptions that make cluster interpretation accessible to non-experts and allow integration of external contextual knowledge beyond the dataset. We systematically evaluate the reliability of these explanations and demonstrate that \langlasso provides an effective first step for engaging broader audiences in cluster interpretation. The tool is available at https://langlasso.vercel.app |
| title | LangLasso: Interactive Cluster Descriptions through LLM Explanation |
| topic | Human-Computer Interaction Machine Learning Computation |
| url | https://arxiv.org/abs/2601.10458 |