# Hierarchical Semantic Retrieval with Cobweb

arXiv: https://arxiv.org/abs/2510.02539 · HTML: https://mlsanity.com/paper/2510.02539/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Discovering Universal Geometry in Embeddings with ICA](https://mlsanity.com/paper/2305.13175/) (2023)
- [EFANNA : An Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph](https://mlsanity.com/paper/1609.07228/) (2016)
- [Explainable Information Retrieval: A Survey](https://mlsanity.com/paper/2211.02405/) (2022)
- [Convolutional Cobweb: A Model of Incremental Learning from 2D Images](https://mlsanity.com/paper/2201.06740/) (2022)
- [Efficient Induction of Language Models Via Probabilistic Concept Formation](https://mlsanity.com/paper/2212.11937/) (2022)
- [Isotropic Representation Can Improve Dense Retrieval](https://mlsanity.com/paper/2209.00218/) (2022)
- [Incremental Concept Formation over Visual Images Without Catastrophic Forgetting](https://mlsanity.com/paper/2402.16933/) (2024)
- [Taxonomic Networks: A Representation for Neuro-Symbolic Pairing](https://mlsanity.com/paper/2505.24601/) (2025)
- [HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2506.14707/) (2025)

## Built on by (most cited first, 4 of 4)

- [LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models](https://mlsanity.com/paper/2607.16305/) (2026)
- [Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals](https://mlsanity.com/paper/2608.21610/) (2026)
- [Diffusion Models and Concept Formation](https://mlsanity.com/paper/2609.13047/) (2026)
- [A Unified Account of Concepts and Chunks](https://mlsanity.com/paper/2609.30414/) (2026)

## Abstract (arXiv)

Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence embeddings into a prototype tree and rank documents via coarse-to-fine traversal. Internal nodes act as concept prototypes, providing multi-granular relevance signals and a transparent rationale through retrieval paths. We instantiate two inference approaches: a generalized best-first search and a lightweight path-sum ranker. We evaluate our approaches on MS MARCO and QQP with encoder (e.g., BERT/T5) and decoder (GPT-2) representations. Our results show that our retrieval approaches match the dot product search on strong encoder embeddings while remaining robust when kNN degrades: with GPT-2 vectors, dot product performance collapses whereas our approaches still retrieve relevant results. Overall, our experiments suggest that Cobweb provides competitive effectiveness, improved robustness to embedding quality, scalability, and interpretable retrieval via hierarchical prototypes.