arXiv AI October 5, 2026 By Haoyang Luo, Linwei Tao, Jie Gui, Xinghao Chen, Chang Xu, Jianyuan Guo, Minjing Dong

Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking

The paper introduces Causal-Invariant Masking (CIM) to better quantify epistemic uncertainty in Multimodal Large Language Models (MLLMs) by measuring semantic shift between original predictions and those conditioned on a causally-focused view. It proposes Semantic Divergence as a core metric that converges to the variance of the model’s sensitivity to non‑causal correlations, and introduces Expected Embedding Drift (EED) as a fast geometric proxy that estimates this shift directly in the embedding space. Experiments demonstrate state‑of‑the‑art uncertainty quantification performance and a nearly 50% speedup with EED.

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 AI.

arXiv Machine Learning

Jun 29

On the Effect of Uncertainty on Layer-wise Inference Dynamics

arXiv:2507. 06722v2 Announce Type: replace-cross Abstract: Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations.

By Sunwoo Kim, Haneul Yoo, Alice Oh

llms safety

arXiv Machine Learning

Jul 1

CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation

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.

By Sanghyuk Chun, William Yang, Amaya Dharmasiri, Olga Russakovsky

llms nlp multimodal benchmarks safety

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 Computer Vision

Sep 10

Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes

arXiv:2512.14177v4 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust uncertainty estimation essential. Recent work on...

By Joseph Hoche, Andrei Bursuc, David Brellmann, Gilles Louppe, Pavel Izmailov, Angela Yao, Gianni Franchi

llms rag computer-vision multimodal benchmarks

arXiv AI

Jul 7

The Anatomy of Uncertainty in LLMs

arXiv:2603. 24967v2 Announce Type: replace Abstract: Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment.

By Aditya Taparia, Ransalu Senanayake, Kowshik Thopalli, Vivek Narayanaswamy

llms safety

arXiv AI

Jun 10

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

arXiv:2606. 09859v1 Announce Type: cross Abstract: MLLMs frequently hallucinate objects inconsistent with visual inputs.

By Yingxuan Zhuang, Jingxiao Yang, Miao Pan, Cheng Tan, Yuxiang Cai, Siwei Tan, Chen Zhi, Xuhong Zhang, Jianwei Yin, Jintao Chen

multimodal safety

One email a morning, machine-written

Related stories

On the Effect of Uncertainty on Layer-wise Inference Dynamics

CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation

Dissecting Training-Free Uncertainty Estimation in Multimodal Large Language Models

Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes

The Anatomy of Uncertainty in LLMs

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding