(V)LMs generalize beyond surface co-occurrence: Evidence from cross-modal number agreement

arXiv:2609.00443 · cs.CL, cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Embeddings — 55× in this paper · explained in 2 episodes
• Generalization — 27× in this paper · explained in 13 episodes
• Abstraction — 26× in this paper · explained in 1 episode
• Interpretability — 8× in this paper · explained in 15 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Distributed Alignment Search — 2× in this paper
• Linear probe — 2× in this paper · explained in 2 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Alternation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Mechanistic interpretability — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• We Can't Understand AI Using our Existing Vocabulary
• RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
• One-shot and few-shot learning of word embeddings
• The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
• minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models
• A systematic framework for generating novel experimental hypotheses from language models
• Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering