Summary of A Survey on Human-centric Llms, by Jing Yi Wang et al.
A Survey on Human-Centric LLMs
by Jing Yi Wang, Nicholas Sukiennik, Tong Li, Weikang Su, Qianyue Hao, Jingbo Xu, Zihan Huang, Fengli Xu, Yong Li
First submitted to arxiv on: 20 Nov 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 survey provides a comprehensive examination of large language models (LLMs) in performing tasks traditionally done by humans, including cognition, decision-making, and social interaction. The evaluation focuses on LLM competencies across key areas such as reasoning, perception, and social cognition, comparing their abilities to human-like skills. The paper also explores real-world applications of LLMs in domains like behavioral science, political science, and sociology, assessing their effectiveness in replicating human behaviors and interactions. Additionally, the survey identifies challenges and future research directions for improving LLM adaptability, emotional intelligence, cultural sensitivity, and frameworks for human-AI collaboration. The paper’s findings can provide insights into the current capabilities and potential of LLMs from a human-centric perspective. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how large language models (LLMs) are getting better at doing things that humans do, like thinking, making decisions, and interacting with each other. Researchers looked at what LLMs can do in different areas, such as understanding, judging, and working together. They also explored how LLMs can be used in real-life situations, like studying human behavior or predicting political outcomes. The authors found that while LLMs have made progress, there are still challenges to overcome, like making them more adaptable and sensitive to emotions and cultures. This study aims to help us understand what LLMs can do and how they might develop in the future. |
