# Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper

arXiv: https://arxiv.org/abs/2406.05806 · HTML: https://mlsanity.com/paper/2406.05806/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 9 Jun 2024.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [PromptTTS: Controllable Text-to-Speech with Text Descriptions](https://mlsanity.com/paper/2211.12171/) (2022)
- [Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers](https://mlsanity.com/paper/2307.03183/) (2023)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation](https://mlsanity.com/paper/2112.06223/) (2021)
- [Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task Generalization](https://mlsanity.com/paper/2305.11095/) (2023)
- [Can Whisper perform speech-based in-context learning?](https://mlsanity.com/paper/2309.07081/) (2023)
- [WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models](https://mlsanity.com/paper/2203.15863/) (2022)
- [LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT](https://mlsanity.com/paper/2306.17103/) (2023)
- [Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision](https://mlsanity.com/paper/2401.00273/) (2023)
- [PhoWhisper: Automatic Speech Recognition for Vietnamese](https://mlsanity.com/paper/2406.02555/) (2024)
- [Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages](https://mlsanity.com/paper/2310.03018/) (2023)
- [Attention-Guided Adaptation for Code-Switching Speech Recognition](https://mlsanity.com/paper/2312.08856/) (2023)

## Built on by (most cited first, 12 of 12)

- [Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation](https://mlsanity.com/paper/2407.09886/) (2024)
- [AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models](https://mlsanity.com/paper/2506.05140/) (2025)
- [Beyond Transcription: Mechanistic Interpretability in ASR](https://mlsanity.com/paper/2508.15882/) (2025)
- [Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning](https://mlsanity.com/paper/2506.21576/) (2025)
- [Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling](https://mlsanity.com/paper/2412.16474/) (2024)
- [Why is prompting hard? Understanding prompts on binary sequence predictors](https://mlsanity.com/paper/2502.10760/) (2025)
- [Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications](https://mlsanity.com/paper/2502.20311/) (2025)
- [Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts](https://mlsanity.com/paper/2506.11079/) (2025)
- [ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models](https://mlsanity.com/paper/2604.10065/) (2026)
- [IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages](https://mlsanity.com/paper/2606.19157/) (2026)
- [No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpus](https://mlsanity.com/paper/2608.28875/) (2026)
- [HearInContext: A Benchmark for Implicit Context in Speech Recognition](https://mlsanity.com/paper/2609.18680/) (2026)

## Abstract (arXiv)

This research explores how the information of prompts interacts with the high-performing speech recognition model, Whisper. We compare its performances when prompted by prompts with correct information and those corrupted with incorrect information. Our results unexpectedly show that Whisper may not understand the textual prompts in a human-expected way. Additionally, we find that performance improvement is not guaranteed even with stronger adherence to the topic information in textual prompts. It is also noted that English prompts generally outperform Mandarin ones on datasets of both languages, likely due to differences in training data distributions for these languages despite the mismatch with pre-training scenarios. Conversely, we discover that Whisper exhibits awareness of misleading information in language tokens by ignoring incorrect language tokens and focusing on the correct ones. In sum, We raise insightful questions about Whisper's prompt understanding and reveal its counter-intuitive behaviors. We encourage further studies.