@kdariina: Why do embedding models struggle with binding, a core requirement for multi-object understanding? We find that objects …
Summary
This thread discusses a finding that embedding models struggle with binding (a core requirement for multi-object understanding) and that solving it requires going beyond the linear representation hypothesis.
View Cached Full Text
Cached at: 07/01/26, 02:09 PM
Why do embedding models struggle with binding, a core requirement for multi-object understanding?
We find that objects don’t decompose into simple components. Binding is possible, but requires going beyond the linear representation hypothesis.
Co-led with @a_uselis 🧵👇 https://t.co/VzTAXB7cGN
Similar Articles
How can embedding models bind concepts?
This paper investigates why CLIP struggles with concept binding, showing that while CLIP's binding function is high-complexity, controlled transformer models can learn low-complexity binding functions through multiplicative interactions that generalize better.
Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization
This paper introduces Text2Opt-Bench, a scalable benchmark for text-to-optimization, and identifies that LLMs struggle with 'binding' (grounding problem data) rather than 'modeling' (choosing optimization structure). The authors propose BIND, a simple inference-time method that externalizes numeric data, significantly improving accuracy across models.
Cell-Based Representation of Relational Binding in Language Models
Study reveals that LLMs encode discourse-level relational binding through Cell-based Binding Representation (CBR), a low-dimensional linear subspace where each cell maps to entity-relation pairs, providing causal evidence for how models track entities and relations.
@mixedbreadai: By now, everyone knows that single-vector embedding models are hugely limiting for modern workflows. But they contain t…
Single-vector embedding models can be used to extract sparse latent terms, and BM25 can turn this vocabulary into a strong retriever.
Your Embedding Model is SMARTer Than You Think
SMART is a framework that unlocks latent multi-vector capabilities in single-vector models for multimodal retrieval, improving state-of-the-art performance with reduced computational costs via contrastive training and late-interaction inference.