On the Theoretical Limitations of Embedding-Based Retrieval
arxiv.org · 8,107 words · saved by 1 readers
N/A
On the Theoretical Limitations of Embedding-Based Retrieval Orion Weller*,1,2 , Michael Boratko1 , Iftekhar Naim1 and Jinhyuk Lee1 1 Google DeepMind, 2 Johns Hopkins University Vector embeddings have been tasked with an ever-increasing set of retrieval tasks over the years, with a nascent rise in using them for reasoning, instruction-following, coding, and more. These new benchmarks…
related reading
- On the Theoretical Limitations of Embedding-Based Retrievalarxiv.org
- [2508.21038] On the Theoretical Limitations of Embedding-Based Retrievalarxiv.org
- Embeddings: What they are and why they mattersimonwillison.net
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- Vector embeddings | OpenAI APIdevelopers.openai.com
- Vector embeddings | OpenAI APIplatform.openai.com
- Foundations of Vector Retrievalarxiv.org
- Better RAG 1: Basicsolickel.com
- Beyond embeddings: Navigating the shift to completions-only RAGsensible.so
- Introducing text and code embeddings | OpenAIopenai.com
- 1301.3781arxiv.org