Summary of Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models, by Sheng-lun Wei et al.
Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models
by Sheng-Lun Wei, Cheng-Kuang Wu, Hen-Hsen Huang, Hsin-Hsi Chen
First submitted to arxiv on: 5 Jun 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 This paper investigates the phenomenon of “selection biases” in Large Language Models (LLMs), specifically focusing on decision-making processes when choosing from an ordered sequence. The authors identify biases related to option order and token usage, which significantly impact model performance. They quantify these biases through empirical analysis across multiple models and tasks, proposing mitigation strategies to enhance model robustness. Key contributions include precisely quantifying the influence of option order and token usage on LLMs, developing strategies to mitigate sensitivity, and providing a detailed analysis of sensitivity across models and tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how Large Language Models (LLMs) make decisions when choosing from a list. The researchers found that these models have biases because of the way they are trained. They looked at two kinds of biases: one related to the order of options, and another related to the words used in those options. They showed that these biases can greatly affect how well the models perform. To fix this, they proposed ways to make the models more robust. |
Keywords
» Artificial intelligence » Token
