# LLM-Augmented Semantic Steering of Text Embedding Projection Spaces

arXiv: https://arxiv.org/abs/2605.01957 · HTML: https://mlsanity.com/paper/2605.01957/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 3 May 2026.

## Builds on (most cited first, 16 of 16)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [The Multilingual Amazon Reviews Corpus](https://mlsanity.com/paper/2010.02573/) (2020)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration](https://mlsanity.com/paper/2404.00405/) (2024)
- [Visual Interaction with Deep Learning Models through Collaborative Semantic Inference](https://mlsanity.com/paper/1907.10739/) (2019)
- [A Survey on Human-Centric LLMs](https://mlsanity.com/paper/2411.14491/) (2024)
- [Semantic Concept Spaces: Guided Topic Model Refinement using Word-Embedding Projections](https://mlsanity.com/paper/1908.00475/) (2019)
- [Mixed Multi-Model Semantic Interaction for Graph-based Narrative Visualizations](https://mlsanity.com/paper/2302.06452/) (2023)
- [Stop Misusing t-SNE and UMAP for Visual Analytics](https://mlsanity.com/paper/2506.08725/) (2025)
- [DeepSI: Interactive Deep Learning for Semantic Interaction](https://mlsanity.com/paper/2305.18357/) (2023)
- [DeepVA: Bridging Cognition and Computation through Semantic Interaction and Deep Learning](https://mlsanity.com/paper/2007.15800/) (2020)
- [Incorporation of Human Knowledge into Data Embeddings to Improve Pattern Significance and Interpretability](https://mlsanity.com/paper/2209.11364/) (2022)
- [ImageSI: Semantic Interaction for Deep Learning Image Projections](https://mlsanity.com/paper/2408.03845/) (2024)
- [Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale](https://mlsanity.com/paper/2504.09283/) (2025)
- [Creating User-steerable Projections with Interactive Semantic Mapping](https://mlsanity.com/paper/2506.15479/) (2025)
- [Visualizing Spatial Semantics of Dimensionally Reduced Text Embeddings](https://mlsanity.com/paper/2409.03949/) (2024)

## Built on by (most cited first, 1 of 1)

- [Scalable Semantic Steering of Embedding Projections](https://mlsanity.com/paper/2607.03978/) (2026)

## Abstract (arXiv)

Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the relationships an analyst intends to examine. Existing semantic interaction approaches encode semantic intent indirectly through geometric constraints or model updates, limiting interpretability and flexibility. We introduce LLM-augmented semantic steering, which enables analysts to express semantic intent by grouping a small set of example documents within the projection. A large language model externalizes this intent as natural-language representations and selectively extends it to related documents; the resulting semantic information is then incorporated into document representations via text augmentation or embedding-level blending, without retraining the underlying models. A case study illustrates how the same corpus can be reorganized from different semantic perspectives, while simulation-based evaluation shows that semantic steering improves global and local alignment with target semantic structures using only minimal interaction. Embedding-level blending further enables continuous and controllable steering of projection layouts. These results position projection spaces as intent-dependent semantic workspaces that can be reshaped through explicit, interpretable, language-mediated interaction.