# XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2606.16137 · HTML: https://mlsanity.com/paper/2606.16137/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models](https://mlsanity.com/paper/2405.09589/) (2024)
- [A Survey on Speech Large Language Models for Understanding](https://mlsanity.com/paper/2410.18908/) (2024)
- [The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance](https://mlsanity.com/paper/2204.05177/) (2022)
- [LLMs for Relational Reasoning: How Far are We?](https://mlsanity.com/paper/2401.09042/) (2024)
- [ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection](https://mlsanity.com/paper/2505.11079/) (2025)
- [A comprehensive study on fidelity metrics for XAI](https://mlsanity.com/paper/2401.10640/) (2024)
- [WavLM model ensemble for audio deepfake detection](https://mlsanity.com/paper/2408.07414/) (2024)
- [Explainable Artificial Intelligence for Medical Applications: A Review](https://mlsanity.com/paper/2412.01829/) (2024)
- [Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning](https://mlsanity.com/paper/2601.02983/) (2026)
- [Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap](https://mlsanity.com/paper/2410.07436/) (2024)
- [DFALLM: Achieving Generalizable Multitask Deepfake Detection by Optimizing Audio LLM Components](https://mlsanity.com/paper/2512.08403/) (2025)
- [Audio Explanation Synthesis with Generative Foundation Models](https://mlsanity.com/paper/2410.07530/) (2024)

## Abstract (arXiv)

Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model decisions, and harder to be understood by human than natural language explanations. Meanwhile, large language model (LLM)-based explanation generation often produces generic and ungrounded descriptions due to the lack of heuristic evidence and task-specific supervision, stemming from limited grounded explanation datasets for SDD. We therefore propose a training-free explanation framework that integrates XAI evidence with multimodal LLMs to generate grounded and specific explanations. Using the PartialSpoof dataset, we construct a grounded explanation dataset and show that methods with XAI increase inside accuracy by over 45%, verified through human evaluation and faithfulness checks.