# Creating Explanations for New Types of Legal AI

> Note: This article is just one of 60+ sections from our full report titled: The 2024 Legal AI Retrospective - Key Lessons from the Past Year .

**Author:** Alex Denne  
**Category:** Guides  
**Published:** 2024-12-18  
**Reading time:** 3 min

**Note:** This article is just one of 60+ sections from our full report titled: [The 2024 Legal AI Retrospective - Key Lessons from the Past Year](https://www.genieai.co/blog/legal-ai). Please download the full report to check any citations.

**Creating Explanations for New Types of AI**

We are trying to figure out ways to get LLMs to explain their thinking, so we can understand and improve them.

**Challenge:** Explaining complex generative AI models like LLMs

**Research Direction:** Explore mechanistic interpretability for deeper understanding

---

This is the Markdown representation of [https://www.genieai.co/blog/legal-ai-xai-new-types](https://www.genieai.co/blog/legal-ai-xai-new-types), provided for AI agents and crawlers. The HTML page is canonical. See [/llms.txt](https://www.genieai.co/llms.txt) for the full content map.