You will receive a document and a set of top-level topics from a topic hierarchy. Your task is to identify generalizable topics within the document that can act as top-level topics in the hierarchy. If any relevant topics are missing from the provided set, please add them. Otherwise, output the existing top-level topics as identified in the document.

[Top-level topics]
{Topics}

[Examples]
Example 1: Duplicate "[1] Chain of thought prompting", returning the existing topic
Document: 
We explore how generating a chain of thought -- a series of intermediate reasoning steps -- significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting. Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier.

Your response: 
[1] Chain of thought prompting: Discusses a method that generates a sequence of short sentences to describe reasoning logics step by step. 

Example 2: Adding "[1] Prompting for Education"
Document: 
Acknowledging AI fallibility is crucial to address the impact of dogmatic overconfidence in possibly erroneous suggestions generated by LLMs. At the same time, it can reduce fear and other negative attitudes toward AI. This necessitates comprehensive AI literacy interventions that educate the public about LLM constraints and effective usage techniques, i.e prompting strategies. With this aim, a pilot educational intervention was performed in a high school with 21 students. It involved presenting high-level concepts about intelligence, AI, and LLMs, followed by practical exercises involving ChatGPT in creating natural educational conversations and applying established prompting strategies. Encouraging preliminary results emerged, including high appreciation of the activity, improved interaction quality with the LLM, reduced negative AI sentiments, and a better grasp of limitations, specifically unreliability, limited understanding of commands leading to unsatisfactory responses, and limited presentation flexibility. Our aim is to explore AI acceptance factors and refine this approach for more controlled future studies

Your response: 
[1] Prompting for Education: Discusses the use case of prompting in pedagogy and classrooms. 


[Instructions]
Step 1: Determine topics mentioned in the document. 
- The topic labels must be as GENERALIZABLE as possible. They must not be document-specific.
- The topics must reflect a SINGLE topic instead of a combination of topics.
- The new topics must have a level number, a short general label, and a topic description. 
- The topics must be broad enough to accommodate future subtopics. 
Step 2: Perform ONE of the following operations: 
1. If there are already duplicates or relevant topics in the hierarchy, output those topics and stop here. 
2. If the document contains no topic, return "None". 
3. Otherwise, add your topic as a top-level topic. Stop here and output the added topic(s). DO NOT add any additional levels.


[Document]
{Document}

Please ONLY return the relevant or modified topics at the top level in the hierarchy.
[Your response]