# Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights

arXiv: https://arxiv.org/abs/2406.17430 · HTML: https://mlsanity.com/paper/2406.17430/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## 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, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs](https://mlsanity.com/paper/2307.08581/) (2023)
- [GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation](https://mlsanity.com/paper/2404.06609/) (2024)
- [CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility](https://mlsanity.com/paper/2307.09705/) (2023)
- [Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations](https://mlsanity.com/paper/2402.12786/) (2024)
- [Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue](https://mlsanity.com/paper/2312.15316/) (2023)
- [Emotion Based Hate Speech Detection using Multimodal Learning](https://mlsanity.com/paper/2202.06218/) (2022)
- [DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances](https://mlsanity.com/paper/2110.07592/) (2021)
- [Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices](https://mlsanity.com/paper/2304.11408/) (2023)

## Built on by (most cited first, 5 of 5)

- [Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Models](https://mlsanity.com/paper/2505.19670/) (2025)
- [Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox](https://mlsanity.com/paper/2605.27772/) (2026)
- [Resurfacing Paralinguistic Awareness in Large Audio Language Models](https://mlsanity.com/paper/2603.11947/) (2026)
- [Instituto de Telecomunicacc~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning](https://mlsanity.com/paper/2506.17019/) (2025)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

Large Multimodal Models (LMMs) have achieved great success recently, demonstrating a strong capability to understand multimodal information and to interact with human users. Despite the progress made, the challenge of detecting high-risk interactions in multimodal settings, and in particular in speech modality, remains largely unexplored. Conventional research on risk for speech modality primarily emphasises the content (e.g., what is captured as transcription). However, in speech-based interactions, paralinguistic cues in audio can significantly alter the intended meaning behind utterances. In this work, we propose a speech-specific risk taxonomy, covering 8 risk categories under hostility (malicious sarcasm and threats), malicious imitation (age, gender, ethnicity), and stereotypical biases (age, gender, ethnicity). Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk. We observe even the latest models remain ineffective to detect various paralinguistic-specific risks in speech (e.g., Gemini 1.5 Pro is performing only slightly above random baseline). Warning: this paper contains biased and offensive examples.