arXiv:2508.08966v2 Announce Type: replace Abstract: The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a gro...
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
The paper argues that feature attribution scores for generative language models lack a fixed meaning because each generated token is both output and input, leading to multiple distinct explanatory questions. It introduces the Attribution Contract framework, which explicitly defines the model score, fixed variables, target output, generation process, and eligible features, showing how these choices affect attribution outcomes. Experiments demonstrate that different contracts (e.g., local next-token vs. prompt-level) and model architectures (mixture-of-experts vs. masked-diffusion) yield markedly different attribution distributions, highlighting the need for careful contract specification.
arXiv:2608. 00076v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text.
The paper proposes that two architectural assumptions—(1) attention and MLPs share a key‑value form <phi(S)>U, and (2) components read from an additive residual stream—are sufficient to answer three interpretability questions: component interaction, information routing, and token attribution. By treating these selections as a computational graph, the authors develop Unpack, a backward attribution method that validates interaction scores, recovered routes, and token attribution against established tests across models ranging from 160M to 6.9B parameters. The study also shows that contribution and causal effect can differ, with a recognizable signature in how components change when a task is removed.
The paper introduces an interventional protocol to assess how vision‑language models (VLMs) explain the impact of missing modalities on their predictions. By comparing the models’ self‑explanations with actual changes observed after restoring missing inputs, the study finds that VLMs routinely overstate the sufficiency of available evidence and underestimate the effect of adding back missing modalities. Across eight open‑weight VLMs and four tasks, the discrepancy between predicted and realized changes is substantial, revealing systematic mischaracterization of modality dependence.
arXiv:2609.37656v1 Announce Type: new Abstract: Large vision-language models (LVLMs) exhibit strong reasoning capabilities, yet the visual and textual evidence supporting the generated responses rema...
arXiv:2603. 13326v2 Announce Type: replace-cross Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision.
MorphoSHAP is a model‑agnostic post‑hoc explanation method that uses morphological shapes—derived from the Tree of Shapes—as the units of attribution in a Shapley game. Each shape is characterized by its scale, geometry, and signed contribution, enabling explanations that reveal where evidence lies, what structural type carries it, and how strongly it influences the prediction. The approach offers spatial, textual, and global class‑level explanations, surpasses existing attribution methods on multiple benchmarks, and is preferred by users in a study.
The paper introduces Synergistic Faithfulness (𝔽_syn), a new metric based on the Shapley Interaction Index that isolates the joint contribution of visual and textual modalities in Vision‑Language Models (VLMs). It demonstrates that existing explainers overemphasize visual salience and fail to capture true cross‑modal synergy, and provides a scalable evaluation framework for auditing VLM reasoning. The authors evaluate nine XAI methods across three VLM architectures and datasets, revealing significant shortcomings in current approaches.
arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.
The paper introduces a method for analyzing how interventions in a prompt affect a language model’s reasoning by using behavioral counterfactuals. It trains a module to edit the residual stream so that the next-token distributions for a fixed response match between a source and a counterfactual prompt, outperforming standard activation reconstruction. The resulting attribution maps and visualizations help identify causally important locations for counterfactual recovery and guide hypothesis testing with activation patching, as demonstrated in a case study on Gemma-4-E4B-it and DeepSeek-R1-0528-Qwen3-8B.