Summary of Legallens: Leveraging Llms For Legal Violation Identification in Unstructured Text, by Dor Bernsohn et al.
LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text
by Dor Bernsohn, Gil Semo, Yaron Vazana, Gila Hayat, Ben Hagag, Joel Niklaus, Rohit Saha, Kyryl Truskovskyi
First submitted to arxiv on: 6 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 presents a study on detecting legal violations within unstructured textual data and associating these violations with potentially affected individuals. It constructs two datasets using Large Language Models (LLMs) validated by domain expert annotators, specifically designed for class-action cases. The experimental design involves fine-tuning models from the BERT family and open-source LLMs, as well as conducting few-shot experiments using closed-source LLMs. The results show that the datasets and setups can be used for both tasks, with F1-scores of 62.69% (violation identification) and 81.02% (associating victims). The paper also publicly releases the datasets and code to advance research in legal natural language processing (NLP). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study creates two special datasets using big computer programs called Large Language Models (LLMs). These datasets help computers understand when laws are being broken and who might be affected. This is important for class-action lawsuits. The researchers tested their methods by fine-tuning some computer models and trying out new ones. They found that their approach worked well, with good results in identifying violations and linking them to people. To help others do the same thing, they shared the datasets and code used in the study. |
Keywords
* Artificial intelligence * Bert * Few shot * Fine tuning * Natural language processing * Nlp
