Summary of On Adversarial Robustness and Out-of-distribution Robustness Of Large Language Models, by April Yang et al.
On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models
by April Yang, Jordan Tab, Parth Shah, Paul Kotchavong
First submitted to arxiv on: 13 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 investigates the connection between robustness to adversarial perturbations and out-of-distribution (OOD) inputs in large language models (LLMs). It addresses a critical gap in evaluating robustness by applying methods designed for one type of robustness across both contexts. The study evaluates performance on benchmark datasets, including accuracy, precision, recall, and F1 scores in various natural language inference tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how well large language models do when faced with tricky inputs that are meant to confuse them or come from outside the usual data they’ve seen. It wants to see if these models can handle both kinds of problems together. To do this, it takes methods designed for one kind of problem and uses them on both types of inputs. The results show how well the model does in different tasks. |
Keywords
» Artificial intelligence » Inference » Precision » Recall
