Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts

arXiv:2609.00293 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/aparaselli/slow-to-see-slow-to-suppress

Terminology

• Ablation — 45× in this paper · explained in 1 episode
• Modality Gap — 12× in this paper · explained in 4 episodes
• Alignment — 10× in this paper · explained in 1 episode
• RAG — 8× in this paper · explained in 3 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 7× in this paper · explained in 3 episodes
• Chain-of-Thought (CoT) — 3× in this paper · explained in 4 episodes
• Core — 3× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation — 3× in this paper
• Pruning — 2× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Chain-of-Thought (CoT) Prompting — 1× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Effect of Chain-of-Thought — 1× in this paper
• Grounding — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• Qwen2.5-VL Technical Report
• Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
• MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
• Ministral 3
• Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
• Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
• Gemma 3 Technical Report
• How Visual Representations Map to Language Feature Space in Multimodal LLMs
• The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

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