paper-with-me

홈 › Papers

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

2024-06-09 · Chih-Kai Yang, Kuan-Po Huang, Hung-Yi Lee

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.

📄 PDF Abstract BibTeX arXiv:2406.05806

Code (1)

b08202033/whisper_prompting 공식 구현 pytorch

Tasks

speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Do Prompt-Based Models Really Understand the Meaning of Their Prompts?

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. Such success can give the impression that prompts help models to learn faster in the same w…

Few-Shot LearningNatural Language Inference

Do Prompt-Based Models Really Understand the Meaning of their Prompts?

2021-09-02 · NAACL 2022 7 · Albert Webson, Ellie Pavlick

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans …

Few-Shot LearningNatural Language Inference

IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models

2023-07-24 · Hiromu Yakura, Masataka Goto

Recent text-to-audio generation techniques have the potential to allow novice users to freely generate music audio. Even if they do not have musical knowledge, such as about chord progressions and instruments, users can …

Audio GenerationMusic Generation

Do We Really Need a Large Number of Visual Prompts?

2023-05-26 · Youngeun Kim, Yuhang Li, Abhishek Moitra, Ruokai Yin 외

Due to increasing interest in adapting models on resource-constrained edges, parameter-efficient transfer learning has been widely explored. Among various methods, Visual Prompt Tuning (VPT), prepending learnable prompts…

Transfer LearningVisual Prompt Tuning

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models

2024-03-26 · Zhiyuan Yu, Xiaogeng Liu, Shunning Liang, Zach Cameron 외

Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasi…