Summary of Revisiting Zero-shot Abstractive Summarization in the Era Of Large Language Models From the Perspective Of Position Bias, by Anshuman Chhabra et al.
Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias
by Anshuman Chhabra, Hadi Askari, Prasant Mohapatra
First submitted to arxiv on: 3 Jan 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 explores the phenomenon of position bias in Large Language Models (LLMs) during zero-shot abstractive summarization. The authors propose a new formulation, position bias, which captures the tendency of LLMs to prioritize certain parts of the input text over others, leading to undesirable behavior. They investigate this bias using four diverse real-world datasets and multiple models, including GPT 3.5-Turbo, Llama-2, Dolly-v2, Pegasus, and BART. The study provides novel insights into the performance and position bias of these models for zero-shot summarization tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how big language models can be tricked into focusing on certain parts of text instead of others. This is called “position bias”. Researchers tested this bias using different models and text datasets to see what happens. They found that some models do this more than others, which affects the way they summarize texts. This study helps us understand how these language models work and how we can use them better. |
Keywords
» Artificial intelligence » Gpt » Llama » Summarization » Zero shot
