# Demystifying Embedding Spaces using Large Language Models

arXiv: https://arxiv.org/abs/2310.04475 · HTML: https://mlsanity.com/paper/2310.04475/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 6 Oct 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [The impossibility of low rank representations for triangle-rich complex networks](https://mlsanity.com/paper/2003.12635/) (2020)
- [On Interpretation and Measurement of Soft Attributes for Recommendation](https://mlsanity.com/paper/2105.09179/) (2021)

## Built on by (most cited first, 17 of 17)

- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [Language Representations Can be What Recommenders Need: Findings and Potentials](https://mlsanity.com/paper/2407.05441/) (2024)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations](https://mlsanity.com/paper/2403.12451/) (2024)
- [Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models](https://mlsanity.com/paper/2505.17051/) (2025)
- [Embedding-Aligned Language Models](https://mlsanity.com/paper/2406.00024/) (2024)
- [Item-Language Model for Conversational Recommendation](https://mlsanity.com/paper/2406.02844/) (2024)
- [Field Matters: A Lightweight LLM-enhanced Method for CTR Prediction](https://mlsanity.com/paper/2505.14057/) (2025)
- [Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?](https://mlsanity.com/paper/2601.04690/) (2026)
- [EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors](https://mlsanity.com/paper/2602.21218/) (2026)
- [Wave Network: An Ultra-Small Language Model](https://mlsanity.com/paper/2411.02674/) (2024)
- [Attacks and Defenses Against LLM Fingerprinting](https://mlsanity.com/paper/2508.09021/) (2025)
- [Synthetic Dialogue Generation for Interactive Conversational Elicitation & Recommendation (ICER)](https://mlsanity.com/paper/2510.02331/) (2025)
- [Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences](https://mlsanity.com/paper/2603.15713/) (2026)
- [GuidelineGuard: An Agentic Framework for Medical Note Evaluation with Guideline Adherence](https://mlsanity.com/paper/2411.06264/) (2024)
- [Descriptive History Representations: Learning Representations by Answering Questions](https://mlsanity.com/paper/2506.02125/) (2025)

## Abstract (arXiv)

Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream tasks make use of these compressed representations, meaningful interpretation usually requires visualization using dimensionality reduction or specialized machine learning interpretability methods. This paper addresses the challenge of making such embeddings more interpretable and broadly useful, by employing Large Language Models (LLMs) to directly interact with embeddings -- transforming abstract vectors into understandable narratives. By injecting embeddings into LLMs, we enable querying and exploration of complex embedding data. We demonstrate our approach on a variety of diverse tasks, including: enhancing concept activation vectors (CAVs), communicating novel embedded entities, and decoding user preferences in recommender systems. Our work couples the immense information potential of embeddings with the interpretative power of LLMs.