Summary of Semrode: Macro Adversarial Training to Learn Representations That Are Robust to Word-level Attacks, by Brian Formento et al.
SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
by Brian Formento, Wenjie Feng, Chuan Sheng Foo, Luu Anh Tuan, See-Kiong Ng
First submitted to arxiv on: 27 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: 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 In this paper, researchers propose a new approach to enhance the robustness of language models (LMs) against adversarial attacks. Specifically, they introduce Semantic Robust Defence (SemRoDe), a macro adversarial training strategy that learns a robust representation by bridging the gap between the base domain and an adversarial domain. The authors demonstrate that their method can be generalized across word embeddings and achieve state-of-the-art robustness on BERT and RoBERTa models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The goal of this paper is to make language models more resistant to attacks. Right now, these models are vulnerable to attacks that change individual words. The researchers want to fix this by teaching the model to be more robust. They use a new way of training the model called SemRoDe, which helps the model understand when it’s seeing an attack or not. This makes the model better at handling attacks it hasn’t seen before. |
Keywords
* Artificial intelligence * Bert
