Summary of Extracting Norms From Contracts Via Chatgpt: Opportunities and Challenges, by Amanul Haque and Munindar P. Singh
Extracting Norms from Contracts Via ChatGPT: Opportunities and Challenges
by Amanul Haque, Munindar P. Singh
First submitted to arxiv on: 2 Apr 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 paper investigates ChatGPT’s effectiveness in extracting norms from contracts, which is crucial for engineering multiagent systems that govern interactions between autonomous parties. The authors extract four types of norms (commitment, prohibition, authorization, and power) along with their associated elements from contracts. While ChatGPT demonstrates promising performance without requiring training or fine-tuning, it also has limitations that lead to incorrect norm extractions, including oversight of crucial details, hallucination, incorrect parsing of conjunctions, and empty norm elements. The authors highlight the importance of enhancing norm extraction for developing transparent and trustworthy formal agent interaction specifications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ChatGPT is a powerful tool that can help extract important rules from contracts. These rules are like guidelines for how different groups or people should behave when working together. The researchers used ChatGPT to look at contracts and see if it could find these rules, or “norms”. They found that ChatGPT was pretty good at doing this, but it wasn’t perfect. Sometimes it missed important details, or made things up that weren’t actually there. This is a problem because if we want to make sure that contracts are fair and honest, we need to be able to extract these rules accurately. |
Keywords
» Artificial intelligence » Fine tuning » Hallucination » Parsing
