Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning

arXiv:2606.01914 · cs.CL, cs.CV · Submitted 2026-06-01 · Read on arXiv

cs.CL, cs.CV

Submitted: 2026-06-01

Updated: 2026-08-31

Terminology

Accuracy — 84× in this paper · explained in 1 episode
Benchmark — 14× in this paper · explained in 2 episodes
Activation Patching — 9× in this paper · explained in 2 episodes
Interpretability — 8× in this paper · explained in 15 episodes
Ablation — 7× in this paper · explained in 1 episode
Grounding — 6× in this paper · explained in 3 episodes
Mechanistic interpretability — 6× in this paper · explained in 2 episodes
Vision-language models — 5× in this paper · explained in 2 episodes
Dog Outdoor — 4× in this paper
Transformer — 4× in this paper · explained in 2 episodes
Visual Grounding — 4× in this paper · explained in 2 episodes
Conference on Computer Vision and Pattern Recognition — 3× in this paper
Dog Raw — 3× in this paper
Linear probe — 3× in this paper · explained in 2 episodes
Adam — 2× in this paper · explained in 2 episodes
Hallucination — 2× in this paper · explained in 4 episodes
Trace — 2× in this paper · explained in 2 episodes
Benchmarking — 1× in this paper · explained in 4 episodes
Direct Preference Optimization — 1× in this paper
Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
Linear Probing — 1× in this paper · explained in 2 episodes
Robustness — 1× in this paper · explained in 5 episodes
Selection Bias — 1× in this paper · explained in 4 episodes
Sparsity — 1× in this paper · explained in 4 episodes