Summary of Event Grounded Criminal Court View Generation with Cooperative (large) Language Models, by Linan Yue et al.
Event Grounded Criminal Court View Generation with Cooperative (Large) Language Models
by Linan Yue, Qi Liu, Lili Zhao, Li Wang, Weibo Gao, Yanqing An
First submitted to arxiv on: 10 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 proposes an Event Grounded Generation (EGG) method for criminal court view generation, leveraging Large Language Models (LLMs). The EGG approach introduces fine-grained event information into text summarization, improving the accuracy and coherence of generated texts. The authors design a LLMs-based extraction method to extract events from case facts without massive annotated data. They then merge these extracted events with case facts for court view generation. To reduce computational burden, they also propose an LLMs-free EGG method that eliminates the need for event extraction using LLMs during inference. Experimental results on a real-world dataset demonstrate the effectiveness of their proposed method. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to generate texts about crimes and court cases. It uses large language models (LLMs) to help extract important events from case facts, making the generated texts more detailed and coherent. The authors also found a way to make this process faster by not needing LLMs during the final step of generating the text. This new method shows promising results on real-world data. |
Keywords
» Artificial intelligence » Inference » Summarization
