Summary of Sensitivity Of Generative Vlms to Semantically and Lexically Altered Prompts, by Sri Harsha Dumpala et al.
Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts
by Sri Harsha Dumpala, Aman Jaiswal, Chandramouli Sastry, Evangelos Milios, Sageev Oore, Hassan Sajjad
First submitted to arxiv on: 16 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Computation and Language (cs.CL); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper evaluates the sensitivity of generative vision-language models (VLMs) to lexical and semantic changes in text prompts using the SugarCrepe++ dataset. The authors analyze how VLMs respond to alterations in prompts without corresponding semantic shifts, demonstrating that these models are highly susceptible to such changes. This vulnerability impacts the performance of techniques designed for output consistency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Generative vision-language models (VLMs) help computers understand and generate text based on images. A new study looks at how well these models work when given changed prompts. The researchers used a special dataset called SugarCrepe++ to test the models’ reactions to changes in words without changing their meaning. They found that VLMs are very sensitive to these changes, which affects how well they can generate consistent text. |
