Summary of Fair In-context Learning Via Latent Concept Variables, by Karuna Bhaila et al.
Fair In-Context Learning via Latent Concept Variables
by Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu, Chen Zhao, Feng Chen, Xintao Wu
First submitted to arxiv on: 4 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
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 inherent bias in large language models (LLMs) when used for predictive tasks in various domains, including high-stakes applications. It highlights how LLMs can inherit social bias and discrimination from their pre-training data, making it crucial to design fair and unbiased systems. The authors propose an optimal demonstration selection approach that utilizes latent concept variables for resource-efficient task adaptation, reducing correlation between predictive outcomes and sensitive variables. They also design data augmentation strategies to promote fairness during latent concept learning and utilize the learned concept to select demonstrations from a training dataset for fair predictions during inference while maintaining model utility. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores how large language models can pick up social biases from their training data, which is important because these models are increasingly being used in high-stakes applications. The researchers want to find ways to make sure these models don’t perpetuate unfair biases. They propose a new approach that uses “latent concept variables” to help the model learn and adapt more fairly. This approach also includes techniques to reduce bias and ensure fair predictions. |
Keywords
» Artificial intelligence » Data augmentation » Inference
