Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
cs.AI, cs.CL, cs.CV, cs.LG
Submitted: 2026-02-27
Updated: 2026-11-13
Code: https://github.com/daohieu17ctt/UMPIRE
Terminology
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Microsoft COCO Captions: Data Collection and Evaluation Server
- SmellNet: A Large-scale Dataset for Real-world Smell Recognition
- GPT-4o System Card
- Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
- Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
- Object Hallucination in Image Captioning
- SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
- Aligning Large Multimodal Models with Factually Augmented RLHF
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective
- VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents