Revisiting Greedy Decoding for Visual Question Answering: A Calibration Perspective

arXiv:2604.23443 · cs.CL · Submitted 2026-04-25 · Read on arXiv

cs.CL

Submitted: 2026-04-25

Updated: 2026-08-31

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 52× in this paper · explained in 2 episodes
• Calibration — 39× in this paper · explained in 7 episodes
• Accuracy — 37× in this paper · explained in 1 episode
• Hallucination — 34× in this paper · explained in 3 episodes
• Brier Score — 7× in this paper
• Verification — 7× in this paper · explained in 2 episodes
• Visual Question Answering — 7× in this paper
• Grounding — 5× in this paper · explained in 3 episodes
• Abstention — 3× in this paper · explained in 1 episode
• Expected Calibration Error — 3× in this paper
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Multimodal Reasoning — 3× in this paper · explained in 5 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 2× in this paper
• Steering — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Epistemic Uncertainty — 1× in this paper · explained in 9 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
• Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
• The Curious Case of Neural Text Degeneration
• Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
• Evaluating Object Hallucination in Large Vision-Language Models
• The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
• ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
• Diversity of Thought Improves Reasoning Abilities of LLMs
• Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
• Calibration in Deep Learning: A Survey of the State-of-the-Art
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language 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