Summary of Llms As Meta-reviewers’ Assistants: a Case Study, by Eftekhar Hossain et al.
LLMs as Meta-Reviewers’ Assistants: A Case Study
by Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal, Alex Knipper, Souvika Sarkar, John Salvador, Yash Mahajan, Sri Guttikonda, Mousumi Akter, Md. Mahadi Hassan, Matthew Freestone, Matthew C. Williams Jr., Dongji Feng, Santu Karmaker
First submitted to arxiv on: 23 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
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 explores whether Large Language Models (LLMs) can aid in composing meta-reviews, which involve summarizing diverse opinions from multiple experts. To achieve this, the authors use three popular LLMs (GPT-3.5, LLaMA2, and PaLM2) to generate controlled multi-perspective summaries (MPSs) of expert opinions. The study prompts the LLMs with different types/levels of prompts based on the TELeR taxonomy and analyzes the generated MPSs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how Large Language Models can help experts summarize other people’s ideas. They test three popular models to see if they can make a summary that shows multiple perspectives. The models are given special prompts to try to get them to understand the different opinions better. Then, the study looks at what the models come up with. |
Keywords
* Artificial intelligence * Gpt
