arXiv Machine Learning July 1, 2026 By Sanghyuk Chun, William Yang, Amaya Dharmasiri, Olga Russakovsky

CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation

Read the original on arXiv Machine Learning →

arXiv:2606. 32012v1 Announce Type: new Abstract: Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 22

Dissecting Training-Free Uncertainty Estimation in Multimodal Large Language Models

arXiv:2609.22206v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of multimodal tasks, yet understanding and quantify...

By Soroush Seifi, Vaggelis Dorovatas, Lin Li, Yarin Gal, Rahaf Aljundi

llms multimodal benchmarks safety

arXiv Computation and Language

Sep 1

Revisiting Greedy Decoding for Visual Question Answering: A Calibration Perspective

The paper argues that stochastic decoding, common in large language models, is not ideal for Visual Question Answering (VQA) because VQA is a closed‑ended task with head‑heavy answer distributions and epistemic uncertainty. The authors formalize how model calibration relates to predictive accuracy and identify conditions under which greedy decoding is optimal. Experiments across multiple benchmarks show greedy decoding outperforms stochastic sampling, and a new Greedy Decoding for Reasoning Models further improves multimodal reasoning performance.

By Boqi Chen, Xudong Liu, Yunke Ao, Jianing Qiu

llms nlp multimodal benchmarks

arXiv Machine Learning

Sep 23

Unified Multimodal Uncertain Inference

Unified Multimodal Uncertain Inference (UMUI) is a new task that requires models to generate calibrated probability estimates for hypotheses conditioned on premises across text, audio, and video modalities. The authors create a human‑annotated evaluation set with scalar probability judgments for audio, visual, and audiovisual settings, and benchmark their approach on existing text and audio datasets. Their CLUE framework, which blends self‑consistent teacher calibration with distribution‑based confidence probing, enables a 3B‑parameter model to match or surpass zero‑shot baselines up to 32B parameters across all modalities.

By Dengjia Zhang, Alexander Martin, William Jurayj, Kenton Murray, Benjamin Van Durme, Reno Kriz

multimodal benchmarks

arXiv AI

Aug 25

Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models

arXiv:2608.22232v1 Announce Type: new Abstract: Real-world situation appearances can deviate from their underlying physical states, challenging the reliability of multimodal large language models (ML...

By Zhiming Yang, Zhuoxi Xiong, Donglin Zhou, Wenjun Wei, Shiyao Cui, Jinqiao Shi

llms fine-tuning multimodal benchmarks

arXiv AI

Aug 17

BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA

arXiv:2603. 28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language models (VLMs).

By Taeyun Roh, Suhyeong Park, Dongyoung Lee, Eunyeong Jo, Wonjune Jang, Junha Jung, Jaewoo Kang

llms nlp efficiency multimodal benchmarks safety

arXiv Computer Vision

Sep 10

Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation

arXiv:2605.27136v2 Announce Type: replace Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deploy...

By Joseph Hoche, David Brellmann, Gianni Franchi

llms multimodal