# When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection

arXiv: https://arxiv.org/abs/2608.30204 · HTML: https://mlsanity.com/paper/2608.30204/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [A Survey on Speech Large Language Models for Understanding](https://mlsanity.com/paper/2410.18908/) (2024)
- [HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement](https://mlsanity.com/paper/2203.13086/) (2022)
- [A Multimodal Corpus for Emotion Recognition in Sarcasm](https://mlsanity.com/paper/2206.02119/) (2022)
- [An Open source Implementation of ITU-T Recommendation P.808 with Validation](https://mlsanity.com/paper/2005.08138/) (2020)
- [MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions](https://mlsanity.com/paper/2302.11824/) (2023)
- [EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning](https://mlsanity.com/paper/2601.15668/) (2026)
- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [The Role of Prosody in Spoken Question Answering](https://mlsanity.com/paper/2502.05389/) (2025)
- [Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech](https://mlsanity.com/paper/2510.25054/) (2025)
- [One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces](https://mlsanity.com/paper/2512.00852/) (2025)

## Built on by (most cited first, 1 of 1)

- [CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection](https://mlsanity.com/paper/2609.16582/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) process speech and text jointly, yet whether they exploit prosodic cues for pragmatic inference or rely on surface acoustic patterns has received little systematic investigation. We address this through sarcasm detection, evaluating Qwen2.5-Omni and Qwen3-Omni on Mandarin Chinese and English under five modality conditions that decompose the contributions of lexical content, vocal semantics, and prosodic structure. Adding audio systematically inflates false positives without improving true positive detection. Acoustic error diagnosis reveals that model errors cluster on a shared stereotype of expressive prosody, namely elevated pitch and irregular pausing, that diverges from the actual cues marking sarcasm in both languages. Targeted manipulation of only these two dimensions causally confirms the heuristic, inducing false positive rates of up to 60%. Applying the same manipulation template to Gemini~3 Flash Preview without modification replicates the effect, suggesting that the stereotype extends beyond the Qwen Omni family rather than arising from a single model architecture.