arXiv AI June 9, 2026 By Jakub Muszy\'nski, Pawe{\l} Pozorski, Maria Ganzha

mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models

arXiv:2606. 07531v1 Announce Type: cross Abstract: We introduce mllm-shap, an open-source Python framework designed to extend Shapley Value (SV) explainability from text-only Large Language Models to Multimodal LLMs (MLLMs) processing joint text and audio inputs.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 9

Bridging Traditional Explainability Methods and Multimodal Multilingual Models: An XAI-Based Analysis

arXiv:2606. 07533v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) effectively integrate text and audio to interpret context in complex interactive dialogues.

By Pawe{\l} Pozorski, Jakub Muszy\'nski, Maria Ganzha

llms nlp multimodal safety

arXiv AI

Jun 2

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.

By Maris Basha, Anja Zai, Sabine Stoll, Richard Hahnloser

rag multimodal benchmarks safety

arXiv Machine Learning

Jul 24

Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models

arXiv:2607. 21496v1 Announce Type: cross Abstract: Cognitive impairment (CI) is a growing public health concern.

By Yingchao Huang, Xin Wang, Yuhan Su, Shanshan Yao

llms rag multimodal benchmarks safety

arXiv AI

Jun 15

The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

arXiv:2606. 14466v1 Announce Type: cross Abstract: This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection.

By Piotr Kit{\l}owski, Dominik Wi\k{a}cek, Mateusz Modrzejewski

robotics benchmarks safety

arXiv Machine Learning

Jun 18

Investigating Faithfulness in Large Audio Language Models

arXiv:2509. 22363v4 Announce Type: replace Abstract: Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks.

By Pooneh Mousavi, Lovenya Jain, Mirco Ravanelli, Cem Subakan

llms multimodal benchmarks safety

arXiv AI

Jun 30

AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification

arXiv:2606. 29335v1 Announce Type: cross Abstract: Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training and testing conditions.

By Chuxiao Zuo, Yao Zhu, Minqiang Xu, Manhong Wang, Yunke Zhang, Fei Huang

rag multimodal

Related stories

Bridging Traditional Explainability Methods and Multimodal Multilingual Models: An XAI-Based Analysis

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models

The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

Investigating Faithfulness in Large Audio Language Models

AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification