From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models

arXiv:2609.32653 · cs.CL, cs.CV · Submitted 2026-09-26 · Read on arXiv

cs.CL, cs.CV

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Benchmark — 47× in this paper · explained in 2 episodes
• Abstention — 45× in this paper · explained in 1 episode
• Accuracy — 34× in this paper · explained in 1 episode
• Verification — 10× in this paper · explained in 2 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Hallucination — 8× in this paper · explained in 3 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Semantic Entropy — 5× in this paper
• F1 Score — 4× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Anchor Loss — 3× in this paper · explained in 1 episode
• Instruction Tuning — 3× in this paper · explained in 2 episodes
• Visual Answerability Diagnosis with Rationales — 3× in this paper
• Visual Contrastive Decoding — 3× in this paper
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Abstention mechanism — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Compositional Spatial Reasoning — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Natural Language Inference (NLI) — 1× in this paper · explained in 2 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

• GPT-4o System Card
• VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

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