Summary of Contextgpt: Infusing Llms Knowledge Into Neuro-symbolic Activity Recognition Models, by Luca Arrotta et al.
ContextGPT: Infusing LLMs Knowledge into Neuro-Symbolic Activity Recognition Models
by Luca Arrotta, Claudio Bettini, Gabriele Civitarese, Michele Fiori
First submitted to arxiv on: 11 Mar 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 proposes a novel approach called ContextGPT for context-aware Human Activity Recognition (HAR) using Large Language Models (LLMs). Traditional NeSy methods rely on ontologies, requiring significant human engineering efforts and domain expertise. ContextGPT leverages pre-trained LLMs to encode common-sense knowledge about human activities in the context they are performed. This approach reduces human effort and expertise requirements compared to ontology-based methods. The paper evaluates ContextGPT’s effectiveness on two public datasets, demonstrating comparable or better recognition rates than logic-based approaches while requiring a fraction of the effort. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research is about improving machines that can recognize human activities based on the context in which they happen. Right now, these systems need lots of labeled data to work well, but it’s hard to get that data. The researchers found that large language models can be used to provide common-sense knowledge about human activities and contexts. They created a new approach called ContextGPT that uses this information to improve the machines’ ability to recognize activities. This method requires less human effort than previous approaches. The researchers tested their method on two public datasets and found that it worked well, sometimes better than other methods. |
Keywords
* Artificial intelligence * Activity recognition
