paper-with-me

Papers

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures

2025-11-27 · Florian Rottach, William Rudman, Bastian Rieck, Harrisen Scells, Carsten Eickhoff arxiv

Studying how embeddings are organized in space not only enhances model interpretability but also uncovers factors that drive downstream task performance. In this paper, we present a comprehensive analysis of topological and geometric measures across a wide set of text embedding models and datasets. We find a high degree of redundancy among these measures and observe that individual metrics often fail to sufficiently differentiate embedding spaces. Building on these insights, we introduce Unified Topological Signatures (UTS), a holistic framework for characterizing embedding spaces. We show that UTS can predict model-specific properties and reveal similarities driven by model architecture. Further, we demonstrate the utility of our method by linking topological structure to ranking effectiveness and accurately predicting document retrievability. We find that a holistic, multi-attribute perspective is essential to understanding and leveraging the geometry of text embeddings.

📄 PDF Abstract BibTeX arXiv:2511.22150

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models

2022-11-16 · Shitao Xiao, Zheng Liu

To better support retrieval applications such as web search and question answering, growing effort is made to develop retrieval-oriented language models. Most of the existing works focus on improving the semantic represe…

Dimensionality ReductionInformation RetrievalQuestion AnsweringRetrieval+2

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

2026-08-18 · Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li 외 arxiv

Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing systems usually rely on prompted expans…

CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval

2023-04-20 · Guangyuan Ma, Xing Wu, Peng Wang, Songlin Hu

Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic d…

Passage RetrievalRetrieval

SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding

2026-04-14 · Shaowen Chen, Zhicheng Liao, Hongwei Wang arxiv

Speculative Decoding (SD) accelerates Large Language Model (LLM) inference by employing a lightweight draft model to propose candidate tokens, which are verified in parallel by the target model, without compromising gene…

Nonparametric Decoding for Generative Retrieval

2022-10-05 · Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh 외

The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametri…

DecoderLanguage ModellingRetrievalText Retrieval