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

• URL: http://arxiv.org/abs/2606.07533v1
• Date: Tue, 21 Apr 2026 11:32:24 GMT
• Title: Bridging Traditional Explainability Methods and Multimodal Multilingual Models: An XAI-Based Analysis
• Abstract summary: Multimodal Large Language Models (MLLMs) integrate text and audio to interpret context in complex interactive dialogues.<n>We formalize a multimodal extension of the Shapley Value framework, treating discrete text tokens and aligned audio segments as cooperative features.<n>We propose Spectrogram-Guided Phonetic Alignment (SGPA), a novel preprocessing method that maps high-frequency audio streams to interpretable, word-aligned segments.
• Score: 1.8352113484137629
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) effectively integrate text and audio to interpret context in complex interactive dialogues. However, the internal mechanisms by which heterogeneous modalities influence model behavior remain opaque. While Shapley Values (SV) provide a robust, model-agnostic framework for local explainability in text-based NLP, their extension to multimodal data is hindered by cross-channel dependencies, intricate dialogue structures, and the prohibitive computational complexity of dense audio representations. In this work, we formalize a multimodal extension of the Shapley Value framework, treating discrete text tokens and aligned audio segments as cooperative features. To ensure computational feasibility, we deploy a suite of efficient estimation strategies: exact SV computation for low-dimensional inputs and sampling-based approximations - including Monte Carlo permutations and stratified sampling with Neyman-optimal allocation - to minimize variance under constrained computational budgets. To resolve the granularity mismatch between modalities, we propose Spectrogram-Guided Phonetic Alignment (SGPA), a novel preprocessing method that maps high-frequency audio streams to interpretable, word-aligned segments. Our contribution is twofold: first, we provide an open-source, model-agnostic Python package and a companion GUI for the computation and interactive visualization of multimodal attributions. Second, we evaluate our framework using curated subsets of the VoiceBench and Infinity Instruct datasets across diverse multilingual scenarios. Our experimental results reveal that input modality is a primary driver of attribution volatility and demonstrate that standard syntactic importance proxies often fail to predict model attention in multimodal, cross-lingual contexts.

Related papers

• mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models [1.8352113484137629]
  mllm-shap is a Python framework designed to extend Shapley Value explainability from text-only Large Language Models to Multimodal LLMs.<n> Modality-aware coalition masking, which manages the interleaved processing of discrete text tokens and dense audio encoder frames.<n>Phonetic alignment-based token grouping, a novel technique that reduces the coalition space by 10x to 50x.
  arXiv  Detail & Related papers  (2026-04-21T10:01:51Z)
• LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation [51.071351994330605]
  Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model.<n>Existing approaches largely rely on implicit or indirect alignment signals and remain suboptimal for simultaneously supporting multimodal understanding and generation.<n>We propose LVRPO, a language-visual reinforcement-based preference optimization framework that explicitly aligns language and visual representations.
  arXiv  Detail & Related papers  (2026-03-29T13:38:21Z)
• PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation [58.1914505657064]
  This paper proposes a simple yet effective parallel cost aggregation (PCA-Seg) paradigm to alleviate the challenge of knowledge interference between class-level semantics and spatial context.<n>Experiments on eight benchmarks show that each parallel block in PCA-Seg adds merely 0.35M parameters while achieving state-of-the-art OSPS performance.
  arXiv  Detail & Related papers  (2026-03-18T09:26:43Z)
• ChatUMM: Robust Context Tracking for Conversational Interleaved Generation [44.19929499646892]
  Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm.<n>We present ChatUMM, a conversational unified model that excels at robust context tracking to sustain interleaved multimodal generation.<n>ChatUMM derives its capabilities from an interleaved multi-turn training strategy that models serialized text-image streams as a continuous conversational flow.
  arXiv  Detail & Related papers  (2026-02-06T07:11:50Z)
• Complementary and Contrastive Learning for Audio-Visual Segmentation [74.11434759171199]
  We present Complementary and Contrastive Transformer (CCFormer), a novel framework adept at processing both local and global information.<n>Our method sets new state-of-the-art benchmarks across the S4, MS3 and AVSS datasets.
  arXiv  Detail & Related papers  (2025-10-11T06:36:59Z)
• Progressive Semantic Residual Quantization for Multimodal-Joint Interest Modeling in Music Recommendation [6.790539226766362]
  We propose a novel multimodal recommendation framework with two stages.<n>In the first stage, our method generates modal-specific and modal-joint semantic IDs.<n>In the second stage, to model multimodal interest of users, a Multi-Codebook Cross-Attention network is designed.
  arXiv  Detail & Related papers  (2025-08-28T02:16:57Z)
• A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition [3.4568313440884837]
  We present the Anchor-based Multimodal Embedding with Semantic Synchronization (A-MESS) framework.<n>We first design an Anchor-based Multimodal Embedding (A-ME) module that employs an anchor-based embedding fusion mechanism to integrate multimodal inputs.<n>We develop a Semantic Synchronization (SS) strategy with the Triplet Contrastive Learning pipeline, which optimize the process by synchronizing multimodal representation with label descriptions.
  arXiv  Detail & Related papers  (2025-03-25T09:09:30Z)
• Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification [55.624946113550195]
  This paper proposes a cross-modal speech co-learning paradigm. Two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Experimental results on the LRSLip3, GridLip, LomGridLip, and VoxLip datasets demonstrate that our proposed method achieves 60% and 20% average relative performance improvement.
  arXiv  Detail & Related papers  (2023-02-22T10:06:37Z)
• Abstractive Sentence Summarization with Guidance of Selective Multimodal Reference [3.505062507621494]
  We propose a Multimodal Hierarchical Selective Transformer (mhsf) model that considers reciprocal relationships among modalities. We evaluate the generalism of proposed mhsf model with the pre-trained+fine-tuning and fresh training strategies.
  arXiv  Detail & Related papers  (2021-08-11T09:59:34Z)
• Linguistic Structure Guided Context Modeling for Referring Image Segmentation [61.701577239317785]
  We propose a "gather-propagate-distribute" scheme to model multimodal context by cross-modal interaction. Our LSCM module builds a Dependency Parsing Tree Word Graph (DPT-WG) which guides all the words to include valid multimodal context of the sentence.
  arXiv  Detail & Related papers  (2020-10-01T16:03:51Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.