# SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mapping

arXiv: https://arxiv.org/abs/2510.11599 · HTML: https://mlsanity.com/paper/2510.11599/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 18 of 18)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://mlsanity.com/paper/2211.13308/) (2022)
- [Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence](https://mlsanity.com/paper/2305.03010/) (2023)
- [Growth rates of modern science: A latent piecewise growth curve approach to model publication numbers from established and new literature databases](https://mlsanity.com/paper/2012.07675/) (2020)
- [Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings](https://mlsanity.com/paper/2202.06671/) (2022)
- [Multi-View Document Representation Learning for Open-Domain Dense Retrieval](https://mlsanity.com/paper/2203.08372/) (2022)
- [Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity](https://mlsanity.com/paper/2111.08366/) (2021)
- [Clinical ModernBERT: An efficient and long context encoder for biomedical text](https://mlsanity.com/paper/2504.03964/) (2025)
- [Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries](https://mlsanity.com/paper/2406.10280/) (2024)
- [Aspect-based Document Similarity for Research Papers](https://mlsanity.com/paper/2010.06395/) (2020)
- [Specialized Document Embeddings for Aspect-based Similarity of Research Papers](https://mlsanity.com/paper/2203.14541/) (2022)
- [Learning Disentangled Representations of Texts with Application to Biomedical Abstracts](https://mlsanity.com/paper/1804.07212/) (2018)
- [Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them](https://mlsanity.com/paper/2503.22006/) (2025)
- [SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts](https://mlsanity.com/paper/2507.13105/) (2025)
- [CitNetExplorer: A new software tool for analyzing and visualizing citation networks](https://mlsanity.com/paper/1404.5322/) (2014)

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

- [Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints](https://mlsanity.com/paper/2609.07595/) (2026)

## Abstract (arXiv)

We propose SemCSE-Multi, a novel unsupervised framework for generating multifaceted embeddings of scientific abstracts, evaluated in the domains of invasion biology and medicine. These embeddings capture distinct, individually specifiable aspects in isolation, thus enabling fine-grained and controllable similarity assessments as well as adaptive, user-driven visualizations of scientific domains. Our approach relies on an unsupervised procedure that produces aspect-specific summarizing sentences and trains embedding models to map semantically related summaries to nearby positions in the embedding space. We then distill these aspect-specific embedding capabilities into a unified embedding model that directly predicts multiple aspect embeddings from a scientific abstract in a single, efficient forward pass. In addition, we introduce an embedding decoding pipeline that decodes embeddings back into natural language descriptions of their associated aspects. Notably, we show that this decoding remains effective even for unoccupied regions in low-dimensional visualizations, thus offering vastly improved interpretability in user-centric settings.