Papers by Maria Ganzha
mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models (2026.acl-demo)
Copied to clipboard
| Challenge: | mllm-shap is an open-source Python platform for researchers and ML practitioners that extends Shapley value (SV) explainability from text-only large languagemodels to multimodal LLMs that process both text and audio. |
| Approach: | They present a framework that extends Shapley value (SV) explainability from text-only large languagemodels to multimodal LLMs thatjointly process text and audio. |
| Outcome: | mllm-shap is the first publicly available framework for complete, reproducible SV-based explainability of text-audioMLLMs. |