Summary of Using Large Language Models For the Interpretation Of Building Regulations, by Stefan Fuchs et al.
Using Large Language Models for the Interpretation of Building Regulations
by Stefan Fuchs, Michael Witbrock, Johannes Dimyadi, Robert Amor
First submitted to arxiv on: 26 Jul 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 potential of large language models (LLMs) in automating compliance checking for construction projects. Specifically, it evaluates the performance of GPT-3.5 in translating building regulations into LegalRuleML format using a few-shot learning setup. The LLM is shown to learn the basic structure of the format with minimal examples and can be further fine-tuned through careful contextualization. Additionally, the paper investigates whether strategies like chain-of-thought reasoning and self-consistency can be applied to this use case. Overall, the study highlights the potential for LLMs to support more efficient and effective compliance checking processes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses big computers to help with building rules. It’s like having a super smart friend who knows lots of things about buildings! The computer is trained on some examples of what the building rules should look like, and then it can create its own versions of those rules. This could make it easier for people to check if buildings are following all the rules. The study shows that this computer is really good at doing this job and might even get better with more training! |
Keywords
* Artificial intelligence * Few shot * Gpt
