Spectra: A Mechanistic Interpretability Library for Vision-Language Models (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing interpretability tools for visionlanguage models are limited to activation probing and saving. |
| Approach: | They propose a library specifically designed for mechanistic interpretability of visionlanguage models that provides unified abstractions for activation patching, attention pattern analysis, and meta-functions across diverse VLM architectures. |
| Outcome: | The proposed library handles architecture-specific complexities while maintaining a simple, high-level interface. |
Similar Papers
From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens (2025.emnlp-demos)
Copied to clipboard
Hala Sheta, Eric Haoran Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi
| Challenge: | Existing vision-language models are based on exactmatch based accuracy and its derivations to evaluate performance. |
| Approach: | They propose a toolkit that supports systematic benchmarking, analysis, and interpretation of vision-language models by extracting intermediate outputs from any layer during the forward pass of open-source VLMs. |
| Outcome: | The proposed toolkit supports 16 state-of-the-art base VLMs and their over 30 variants and is extensible to accommodate new models without changing the core logic. |
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation (2025.naacl-long)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) have gained prominence due to their success in solving complex cross-modal tasks. |
| Approach: | They propose a Gaussian-Noise-free pipeline for mechanistic interpretability in VLMs that introduces Semantic Image Pairs corruption, the first visual counterpart to Symmetric Token Replacement for text. |
| Outcome: | The proposed pipeline identifies a set of “universal attention heads” in BLIP and LLaVA that consistently contribute across different tasks and modalities. |
Can VLMs Actually See and Read? A Survey on Modality Collapse in Vision-Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Vision-language models integrate textual and visual information, enabling them to process visual inputs and generate predictions. |
| Approach: | They review work on modality collapse analysis to provide insights into the reason for this unintended behavior and review probing studies for fine-grained vision-language understanding. |
| Outcome: | The proposed models can achieve competitive performance in vision-language tasks despite relying heavily on textual information and ignoring visual information. |
Interpreto: An Explainability Library for Transformers (2026.acl-demo)
Copied to clipboard
Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, Charlotte Claye, Francois Hoofd, Raphael Bernas, Nicholas Asher, Celine Hudelot, Fanny Jourdan
| Challenge: | Interpreto is an open-source Python library for interpreting HuggingFace language models . it provides attribution methods and concept-based explanations . documentation or metrics are sometimes missing due to the complexity of the pipeline . |
| Approach: | Interpreto is an open-source Python library for interpreting HuggingFace language models . it provides attribution methods and concept-based explanations . authors welcome issues and pull requests . |
| Outcome: | Interpreto is an open-source Python library for interpreting HuggingFace language models . it provides attribution methods and concept-based explanations . the library welcomes issues and pull requests . |
CIVET: Systematic Evaluation of Understanding in VLMs (2025.findings-emnlp)
Copied to clipboard
Massimo Rizzoli, Simone Alghisi, Olha Khomyn, Gabriel Roccabruna, Seyed Mahed Mousavi, Giuseppe Riccardi
| Challenge: | Current Vision-Language Models can accurately recognize only a limited set of basic object properties; 3) they struggle to understand basic relations among objects. |
| Approach: | They propose a framework that evaluates VLMs on exhaustive sets of stimuli, free from annotation noise, dataset-specific biases, and uncontrolled scene complexity. |
| Outcome: | The proposed framework addresses the lack of standardized systematic evaluation for assessing VLMs’ understanding, enabling researchers to test hypotheses with statistical rigor. |
Towards Explainable Evaluation of Language Models on the Semantic Similarity of Visual Concepts (2022.coling-1)
Copied to clipboard
Maria Lymperaiou, George Manoliadis, Orfeas Menis Mastromichalakis, Edmund G. Dervakos, Giorgos Stamou
| Challenge: | Recent advances in NLP research have focused on robustness and explainability issues of their evaluation strategies. |
| Approach: | They propose to use pre-trained transformers to evaluate semantic similarity for visual vocabularies . they propose to provide explainable metrics for understanding the quality of retrieved instances . |
| Outcome: | The proposed metrics highlight inabilities of widely used evaluation methods and highlight weaknesses in learned linguistic representations. |
Vision-Language Models Align with Human Neural Representations in Concept Processing (2026.eacl-long)
Copied to clipboard
| Challenge: | Recent studies suggest that transformer-based vision-language models capture the multimodality of concept processing in the human brain. |
| Approach: | They analysed multiple VLMs employing different strategies to integrate visual and textual modalities, along with language-only counterparts. |
| Outcome: | The transformer-based vision-language models outperform language-only models in two experimental conditions, while only some outperformed the language-based models. |
Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on explainable AI focus on post-hoc explanation methods that interpret trained models through external approximations. |
| Approach: | They propose to categorize existing approaches into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction. |
| Outcome: | The proposed approaches are categorized into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction. |
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Vision-Language Models (VLMs) have broadened the scope of multimodal applications, but evaluations often neglect abstract dimensions such as personality traits and human values. |
| Approach: | They propose a Visual Question Answering (VQA) benchmark based on Schwartz’s value dimensions that capture core human values guiding people’s preferences and actions. |
| Outcome: | The proposed model can be used to evaluate visual question answering (VQA) tasks and to simulate diverse personas. |
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models (2020.emnlp-demos)
Copied to clipboard
Ian Tenney, James Wexler, Jasmijn Bastings, Tolga Bolukbasi, Andy Coenen, Sebastian Gehrmann, Ellen Jiang, Mahima Pushkarna, Carey Radebaugh, Emily Reif, Ann Yuan
| Challenge: | Existing tools for modeling and understanding models are limited . existing tools can assist practitioners in understanding and evaluating models . |
| Approach: | They present an open-source platform for visualization and understanding of NLP models. |
| Outcome: | The language interpretability tool (lit) is an open-source platform for visualization and understanding of NLP models. |